Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2587 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.5613. Min Act: -0.1700
Data Index: 7766569 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.4050. Min Act: -0.1700
Data Index: 235240 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.3113. Min Act: -0.1700
Data Index: 3144815 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.3113. Min Act: -0.1700
Data Index: 8502315 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.3113. Min Act: -0.1700
Data Index: 1336494 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2800. Min Act: -0.1700
Data Index: 5650674 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2488. Min Act: -0.1700
Data Index: 7546485 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2175. Min Act: -0.1700
Data Index: 1527941 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.1238. Min Act: -0.1700
Data Index: 3073326 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.1863. Min Act: -0.1700
Data Index: 8743905 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.1238. Min Act: -0.1700
Data Index: 8309375 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.0925. Min Act: -0.1700
Data Index: 235232 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.1238. Min Act: -0.1700
Data Index: 1223402 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.0925. Min Act: -0.1700
Data Index: 448007 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.0925. Min Act: -0.1700
Data Index: 5266589 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.0613. Min Act: -0.1700
Data Index: 1060178 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.0613. Min Act: -0.1700
Data Index: 6305803 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.0613. Min Act: -0.1700
Data Index: 1060177 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.0613. Min Act: -0.1700
Data Index: 7745321 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.0300. Min Act: -0.1700
Data Index: 7298207 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19