Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4957 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.7588. Min Act: -0.1700
Data Index: 6419816 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.5713. Min Act: -0.1700
Data Index: 2311111 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.5713. Min Act: -0.1700
Data Index: 3435258 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.5088. Min Act: -0.1700
Data Index: 6577799 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.4463. Min Act: -0.1700
Data Index: 7151501 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.4150. Min Act: -0.1700
Data Index: 3160374 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.4150. Min Act: -0.1700
Data Index: 5798007 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.4150. Min Act: -0.1700
Data Index: 7773545 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.3525. Min Act: -0.1700
Data Index: 7880563 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.3525. Min Act: -0.1700
Data Index: 1196331 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.3525. Min Act: -0.1700
Data Index: 1749419 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.3213. Min Act: -0.1700
Data Index: 1600198 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.3213. Min Act: -0.1700
Data Index: 7398101 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.2900. Min Act: -0.1700
Data Index: 7699445 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.2900. Min Act: -0.1700
Data Index: 8468159 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.2588. Min Act: -0.1700
Data Index: 1921878 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.2588. Min Act: -0.1700
Data Index: 3811813 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.2588. Min Act: -0.1700
Data Index: 2690845 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.2588. Min Act: -0.1700
Data Index: 8174761 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7588. Min Range: -6.7588
Max Act: 6.2588. Min Act: -0.1700
Data Index: 7363476 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19