Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4336 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.6898. Min Act: -0.1700
Data Index: 6357809 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.6586. Min Act: -0.1700
Data Index: 1422673 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.5336. Min Act: -0.1700
Data Index: 7413371 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.5336. Min Act: -0.1700
Data Index: 5201967 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.5336. Min Act: -0.1700
Data Index: 7200458 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.5023. Min Act: -0.1700
Data Index: 3916500 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.5336. Min Act: -0.1700
Data Index: 4262052 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.4398. Min Act: -0.1700
Data Index: 6177547 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.4086. Min Act: -0.1700
Data Index: 3579089 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.4086. Min Act: -0.1700
Data Index: 2352742 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.4086. Min Act: -0.1700
Data Index: 1325286 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.3773. Min Act: -0.1700
Data Index: 7301809 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.3773. Min Act: -0.1700
Data Index: 6298877 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.3773. Min Act: -0.1700
Data Index: 1173623 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.3461. Min Act: -0.1700
Data Index: 4449435 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.3148. Min Act: -0.1700
Data Index: 6923897 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.3773. Min Act: -0.1700
Data Index: 720655 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.3461. Min Act: -0.1700
Data Index: 3074205 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.3148. Min Act: -0.1700
Data Index: 822731 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6898. Min Range: -7.6898
Max Act: 7.2836. Min Act: -0.1700
Data Index: 7493555 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19