Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.8610. Min Act: -0.1700
Data Index: 1203341 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.7985. Min Act: -0.1700
Data Index: 2843569 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.7985. Min Act: -0.1700
Data Index: 2882771 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.7360. Min Act: -0.1700
Data Index: 7989299 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.7360. Min Act: -0.1700
Data Index: 5520391 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.7360. Min Act: -0.1700
Data Index: 2321882 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.6735. Min Act: -0.1700
Data Index: 600281 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.6110. Min Act: -0.1700
Data Index: 4962458 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.5485. Min Act: -0.1700
Data Index: 1994490 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.5485. Min Act: -0.1700
Data Index: 8717397 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.5485. Min Act: -0.1700
Data Index: 5835234 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.5485. Min Act: -0.1700
Data Index: 8717398 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.5485. Min Act: -0.1700
Data Index: 4719298 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.5485. Min Act: -0.1700
Data Index: 2926796 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.5485. Min Act: -0.1700
Data Index: 4431457 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.5485. Min Act: -0.1700
Data Index: 1609989 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.5485. Min Act: -0.1700
Data Index: 6985669 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.4235. Min Act: -0.1700
Data Index: 293405 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.4860. Min Act: -0.1700
Data Index: 5164506 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8610. Min Range: -8.8610
Max Act: 8.4235. Min Act: -0.1700
Data Index: 2795218 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19