Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2613 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.6495. Min Act: -0.1700
Data Index: 4625844 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.4620. Min Act: -0.1700
Data Index: 2264894 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.4307. Min Act: -0.1700
Data Index: 5164968 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.4307. Min Act: -0.1700
Data Index: 4031846 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.4307. Min Act: -0.1700
Data Index: 8326245 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.3995. Min Act: -0.1700
Data Index: 1576068 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.3370. Min Act: -0.1700
Data Index: 1275449 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.3057. Min Act: -0.1700
Data Index: 3559902 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.3057. Min Act: -0.1700
Data Index: 3460024 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.2432. Min Act: -0.1700
Data Index: 147727 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.2432. Min Act: -0.1700
Data Index: 2909122 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.2120. Min Act: -0.1700
Data Index: 4578098 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.2120. Min Act: -0.1700
Data Index: 5410270 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.2120. Min Act: -0.1700
Data Index: 3412993 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.1807. Min Act: -0.1700
Data Index: 3340231 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.1807. Min Act: -0.1700
Data Index: 4068376 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.1807. Min Act: -0.1700
Data Index: 6412691 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.1495. Min Act: -0.1700
Data Index: 3664928 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.1807. Min Act: -0.1700
Data Index: 5849542 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6495. Min Range: -7.6495
Max Act: 7.1495. Min Act: -0.1700
Data Index: 871576 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19