Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.8795. Min Act: -0.1700
Data Index: 2460126 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.6295. Min Act: -0.1700
Data Index: 8435720 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.6295. Min Act: -0.1700
Data Index: 7676813 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.5670. Min Act: -0.1700
Data Index: 1422193 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.5045. Min Act: -0.1700
Data Index: 7973327 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.5045. Min Act: -0.1700
Data Index: 6359764 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.4420. Min Act: -0.1700
Data Index: 5819487 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.5045. Min Act: -0.1700
Data Index: 8461899 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.4420. Min Act: -0.1700
Data Index: 8714042 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.4420. Min Act: -0.1700
Data Index: 5427665 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.3795. Min Act: -0.1700
Data Index: 3931258 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.3795. Min Act: -0.1700
Data Index: 3534232 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.3170. Min Act: -0.1700
Data Index: 2955067 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.2545. Min Act: -0.1700
Data Index: 6963345 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.2545. Min Act: -0.1700
Data Index: 2323371 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.2545. Min Act: -0.1700
Data Index: 8148467 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.1295. Min Act: -0.1700
Data Index: 5086811 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.1920. Min Act: -0.1700
Data Index: 4631056 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.2545. Min Act: -0.1700
Data Index: 6177560 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8795. Min Range: -11.8795
Max Act: 11.1920. Min Act: -0.1700
Data Index: 3145440 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19