Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5669 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.9112. Min Act: -0.1700
Data Index: 6601308 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.6299. Min Act: -0.1700
Data Index: 579046 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.5674. Min Act: -0.1700
Data Index: 985433 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.4737. Min Act: -0.1700
Data Index: 8751835 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.4424. Min Act: -0.1700
Data Index: 8602471 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.4424. Min Act: -0.1700
Data Index: 2203951 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.4112. Min Act: -0.1700
Data Index: 3127871 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.4112. Min Act: -0.1700
Data Index: 111150 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.3799. Min Act: -0.1700
Data Index: 204557 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.3799. Min Act: -0.1700
Data Index: 6512239 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.3174. Min Act: -0.1700
Data Index: 1622183 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.3174. Min Act: -0.1700
Data Index: 1235832 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.3174. Min Act: -0.1700
Data Index: 4302144 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.3174. Min Act: -0.1700
Data Index: 4352193 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.2862. Min Act: -0.1700
Data Index: 402335 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.2549. Min Act: -0.1700
Data Index: 342136 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.2237. Min Act: -0.1700
Data Index: 1865592 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.2237. Min Act: -0.1700
Data Index: 561630 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.2549. Min Act: -0.1700
Data Index: 535772 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9112. Min Range: -5.9112
Max Act: 5.1924. Min Act: -0.1700
Data Index: 6667259 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19