Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.3147. Min Act: -0.1700
Data Index: 5535362 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.2834. Min Act: -0.1700
Data Index: 8758692 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.1272. Min Act: -0.1700
Data Index: 4836350 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.1272. Min Act: -0.1700
Data Index: 4493325 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.0959. Min Act: -0.1700
Data Index: 7408084 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.0334. Min Act: -0.1700
Data Index: 5523070 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.0647. Min Act: -0.1700
Data Index: 1772009 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.0334. Min Act: -0.1700
Data Index: 3830932 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.0022. Min Act: -0.1700
Data Index: 1783295 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.0022. Min Act: -0.1700
Data Index: 6621575 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.0334. Min Act: -0.1700
Data Index: 878688 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.0022. Min Act: -0.1700
Data Index: 5313538 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3147. Min Range: -5.3147
Max Act: 5.0022. Min Act: -0.1700
Data Index: 5389017 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3147. Min Range: -5.3147
Max Act: 4.9709. Min Act: -0.1700
Data Index: 6423314 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3147. Min Range: -5.3147
Max Act: 4.9709. Min Act: -0.1700
Data Index: 174154 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3147. Min Range: -5.3147
Max Act: 4.9709. Min Act: -0.1700
Data Index: 419990 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3147. Min Range: -5.3147
Max Act: 4.9397. Min Act: -0.1700
Data Index: 5661079 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3147. Min Range: -5.3147
Max Act: 4.9397. Min Act: -0.1700
Data Index: 1398649 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3147. Min Range: -5.3147
Max Act: 4.9084. Min Act: -0.1700
Data Index: 707589 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3147. Min Range: -5.3147
Max Act: 4.9397. Min Act: -0.1700
Data Index: 1258840 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19