Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.6633. Min Act: -0.1700
Data Index: 4395116 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.5383. Min Act: -0.1700
Data Index: 1084802 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.5070. Min Act: -0.1700
Data Index: 1263262 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.4758. Min Act: -0.1700
Data Index: 6522186 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.4133. Min Act: -0.1700
Data Index: 2103351 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.4445. Min Act: -0.1700
Data Index: 6679783 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.4133. Min Act: -0.1700
Data Index: 2769532 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.3508. Min Act: -0.1700
Data Index: 3654770 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.4133. Min Act: -0.1700
Data Index: 2645585 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.3508. Min Act: -0.1700
Data Index: 5624450 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.3195. Min Act: -0.1700
Data Index: 3539895 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.3508. Min Act: -0.1700
Data Index: 4523999 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.3508. Min Act: -0.1700
Data Index: 3457739 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.3195. Min Act: -0.1700
Data Index: 3442946 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.3195. Min Act: -0.1700
Data Index: 5410243 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.2883. Min Act: -0.1700
Data Index: 2585503 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.2883. Min Act: -0.1700
Data Index: 7117309 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.2570. Min Act: -0.1700
Data Index: 2027120 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.2258. Min Act: -0.1700
Data Index: 6463826 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6633. Min Range: -6.6633
Max Act: 6.2258. Min Act: -0.1700
Data Index: 1052252 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19