Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2585 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.1190. Min Act: -0.1700
Data Index: 2092770 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.1032. Min Act: -0.1700
Data Index: 3404084 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.1032. Min Act: -0.1700
Data Index: 5229656 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0717. Min Act: -0.1700
Data Index: 6318042 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0559. Min Act: -0.1700
Data Index: 966650 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0559. Min Act: -0.1700
Data Index: 1275124 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0717. Min Act: -0.1700
Data Index: 4666484 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0559. Min Act: -0.1700
Data Index: 1799631 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0559. Min Act: -0.1700
Data Index: 8338512 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0559. Min Act: -0.1700
Data Index: 3106617 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0244. Min Act: -0.1700
Data Index: 4627269 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0086. Min Act: -0.1700
Data Index: 1716667 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0244. Min Act: -0.1700
Data Index: 1218468 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0244. Min Act: -0.1700
Data Index: 1353886 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0086. Min Act: -0.1700
Data Index: 8375797 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1190. Min Range: -3.1190
Max Act: 3.0086. Min Act: -0.1700
Data Index: 6978273 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1190. Min Range: -3.1190
Max Act: 2.9928. Min Act: -0.1700
Data Index: 4767738 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1190. Min Range: -3.1190
Max Act: 2.9611. Min Act: -0.1700
Data Index: 1498928 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1190. Min Range: -3.1190
Max Act: 2.9928. Min Act: -0.1700
Data Index: 1195624 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1190. Min Range: -3.1190
Max Act: 2.9611. Min Act: -0.1700
Data Index: 5818143 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19