Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.5215. Min Act: -0.1700
Data Index: 3718282 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.5215. Min Act: -0.1700
Data Index: 2581100 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.4277. Min Act: -0.1700
Data Index: 6096985 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.3965. Min Act: -0.1700
Data Index: 518159 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.3652. Min Act: -0.1700
Data Index: 2485799 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.3652. Min Act: -0.1700
Data Index: 830151 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.3340. Min Act: -0.1700
Data Index: 8040390 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.3340. Min Act: -0.1700
Data Index: 2731616 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.3027. Min Act: -0.1700
Data Index: 8596229 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.3027. Min Act: -0.1700
Data Index: 948467 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.3027. Min Act: -0.1700
Data Index: 2917396 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.2715. Min Act: -0.1700
Data Index: 8350689 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.2715. Min Act: -0.1700
Data Index: 2953556 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.2402. Min Act: -0.1700
Data Index: 3277796 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.2090. Min Act: -0.1700
Data Index: 4575342 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.2402. Min Act: -0.1700
Data Index: 7017773 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.2090. Min Act: -0.1700
Data Index: 5107511 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.2090. Min Act: -0.1700
Data Index: 5958642 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.1777. Min Act: -0.1700
Data Index: 7021566 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5215. Min Range: -6.5215
Max Act: 6.1465. Min Act: -0.1700
Data Index: 7743299 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19