Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 376 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.7998. Min Act: -0.1700
Data Index: 7347027 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.6436. Min Act: -0.1700
Data Index: 898623 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.6436. Min Act: -0.1700
Data Index: 5055524 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.6436. Min Act: -0.1700
Data Index: 8269464 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.6123. Min Act: -0.1700
Data Index: 8829506 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.6123. Min Act: -0.1700
Data Index: 3030468 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.5811. Min Act: -0.1700
Data Index: 6592021 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.5811. Min Act: -0.1700
Data Index: 4865557 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.5498. Min Act: -0.1700
Data Index: 8805686 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.5811. Min Act: -0.1700
Data Index: 739655 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.5811. Min Act: -0.1700
Data Index: 735704 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.6123. Min Act: -0.1700
Data Index: 1524400 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.5811. Min Act: -0.1700
Data Index: 217625 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.5186. Min Act: -0.1700
Data Index: 60373 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.5186. Min Act: -0.1700
Data Index: 3589621 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.5186. Min Act: -0.1700
Data Index: 3304941 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.5186. Min Act: -0.1700
Data Index: 3933340 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.4873. Min Act: -0.1700
Data Index: 1781213 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.4561. Min Act: -0.1700
Data Index: 5273157 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7998. Min Range: -4.7998
Max Act: 4.4561. Min Act: -0.1700
Data Index: 879656 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19