Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 303 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.8743. Min Act: -0.1700
Data Index: 3217839 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.7493. Min Act: -0.1700
Data Index: 3217835 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.5305. Min Act: -0.1700
Data Index: 7983521 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.5305. Min Act: -0.1700
Data Index: 1274466 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.5305. Min Act: -0.1700
Data Index: 7983509 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.4993. Min Act: -0.1700
Data Index: 2762870 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.4368. Min Act: -0.1700
Data Index: 8744587 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.4993. Min Act: -0.1700
Data Index: 2142316 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.4680. Min Act: -0.1700
Data Index: 7557923 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.4368. Min Act: -0.1700
Data Index: 6632610 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.4055. Min Act: -0.1700
Data Index: 8379000 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.3430. Min Act: -0.1700
Data Index: 3235944 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.3743. Min Act: -0.1700
Data Index: 3866412 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.3743. Min Act: -0.1700
Data Index: 7557925 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.3743. Min Act: -0.1700
Data Index: 2021931 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.3430. Min Act: -0.1700
Data Index: 3235945 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.3430. Min Act: -0.1700
Data Index: 5806562 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.3743. Min Act: -0.1700
Data Index: 2021932 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.3743. Min Act: -0.1700
Data Index: 2652265 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8743. Min Range: -6.8743
Max Act: 6.3743. Min Act: -0.1700
Data Index: 3991007 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19