Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4332. Min Range: -3.4332
Max Act: 3.4332. Min Act: -0.1700
Data Index: 8088537 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4332. Min Range: -3.4332
Max Act: 3.4332. Min Act: -0.1700
Data Index: 5157674 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4332. Min Range: -3.4332
Max Act: 3.3548. Min Act: -0.1700
Data Index: 762227 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4332. Min Range: -3.4332
Max Act: 3.2134. Min Act: -0.1700
Data Index: 5716087 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4332. Min Range: -3.4332
Max Act: 3.1820. Min Act: -0.1700
Data Index: 1369321 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4332. Min Range: -3.4332
Max Act: 3.1348. Min Act: -0.1700
Data Index: 1560727 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4332. Min Range: -3.4332
Max Act: 3.1348. Min Act: -0.1700
Data Index: 8027720 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4332. Min Range: -3.4332
Max Act: 3.0244. Min Act: -0.1700
Data Index: 7109187 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4332. Min Range: -3.4332
Max Act: 3.0086. Min Act: -0.1700
Data Index: 2214355 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4332. Min Range: -3.4332
Max Act: 3.0086. Min Act: -0.1700
Data Index: 4675513 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4332. Min Range: -3.4332
Max Act: 2.9770. Min Act: -0.1700
Data Index: 6025328 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4332. Min Range: -3.4332
Max Act: 2.9295. Min Act: -0.1700
Data Index: 6796315 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4332. Min Range: -3.4332
Max Act: 2.9453. Min Act: -0.1700
Data Index: 3518429 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4332. Min Range: -3.4332
Max Act: 2.9453. Min Act: -0.1700
Data Index: 2367561 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4332. Min Range: -3.4332
Max Act: 2.9295. Min Act: -0.1700
Data Index: 4188282 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4332. Min Range: -3.4332
Max Act: 2.8978. Min Act: -0.1700
Data Index: 4413195 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4332. Min Range: -3.4332
Max Act: 2.9136. Min Act: -0.1700
Data Index: 4987075 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4332. Min Range: -3.4332
Max Act: 2.9295. Min Act: -0.1700
Data Index: 8341700 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4332. Min Range: -3.4332
Max Act: 2.9136. Min Act: -0.1700
Data Index: 3453799 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4332. Min Range: -3.4332
Max Act: 2.8661. Min Act: -0.1700
Data Index: 3611676 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19