Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4495 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2816. Min Range: -7.2816
Max Act: 7.2816. Min Act: -0.1700
Data Index: 1904324 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2816. Min Range: -7.2816
Max Act: 7.1879. Min Act: -0.1700
Data Index: 4614695 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2816. Min Range: -7.2816
Max Act: 7.0941. Min Act: -0.1700
Data Index: 388779 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2816. Min Range: -7.2816
Max Act: 7.0941. Min Act: -0.1700
Data Index: 5545202 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2816. Min Range: -7.2816
Max Act: 7.0941. Min Act: -0.1700
Data Index: 5507396 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2816. Min Range: -7.2816
Max Act: 7.0004. Min Act: -0.1700
Data Index: 4669255 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2816. Min Range: -7.2816
Max Act: 7.0004. Min Act: -0.1700
Data Index: 7841282 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2816. Min Range: -7.2816
Max Act: 7.0004. Min Act: -0.1700
Data Index: 3159775 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.9691. Min Act: -0.1700
Data Index: 8258807 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.9379. Min Act: -0.1700
Data Index: 1024523 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.9066. Min Act: -0.1700
Data Index: 525334 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.8754. Min Act: -0.1700
Data Index: 5511617 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.8754. Min Act: -0.1700
Data Index: 2800765 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.8754. Min Act: -0.1700
Data Index: 4898717 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.8441. Min Act: -0.1700
Data Index: 6184748 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.8441. Min Act: -0.1700
Data Index: 5236999 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.8754. Min Act: -0.1700
Data Index: 2015416 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.8441. Min Act: -0.1700
Data Index: 2708195 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.7816. Min Act: -0.1700
Data Index: 863164 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2816. Min Range: -7.2816
Max Act: 6.8129. Min Act: -0.1700
Data Index: 5484113 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19