Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5192 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.8002. Min Act: -0.1700
Data Index: 1667876 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.7065. Min Act: -0.1700
Data Index: 6519426 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.7065. Min Act: -0.1700
Data Index: 317541 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.7065. Min Act: -0.1700
Data Index: 4727613 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.6752. Min Act: -0.1700
Data Index: 6301519 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.6752. Min Act: -0.1700
Data Index: 8415545 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.6752. Min Act: -0.1700
Data Index: 5903193 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.6440. Min Act: -0.1700
Data Index: 7141220 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.6440. Min Act: -0.1700
Data Index: 2614244 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.6440. Min Act: -0.1700
Data Index: 5592368 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.6127. Min Act: -0.1700
Data Index: 944750 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.5815. Min Act: -0.1700
Data Index: 3480747 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.5815. Min Act: -0.1700
Data Index: 7432114 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.5815. Min Act: -0.1700
Data Index: 995990 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.5815. Min Act: -0.1700
Data Index: 1465950 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.5502. Min Act: -0.1700
Data Index: 5522900 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.5502. Min Act: -0.1700
Data Index: 2043130 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.5815. Min Act: -0.1700
Data Index: 4734018 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.5502. Min Act: -0.1700
Data Index: 835336 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8002. Min Range: -6.8002
Max Act: 6.5190. Min Act: -0.1700
Data Index: 4030865 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19