Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5688 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9667. Min Range: -7.9667
Max Act: 7.9667. Min Act: -0.1700
Data Index: 6183840 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9667. Min Range: -7.9667
Max Act: 7.2479. Min Act: -0.1700
Data Index: 8503590 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9667. Min Range: -7.9667
Max Act: 7.2167. Min Act: -0.1700
Data Index: 6810899 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9667. Min Range: -7.9667
Max Act: 7.1542. Min Act: -0.1700
Data Index: 3760264 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9667. Min Range: -7.9667
Max Act: 7.1542. Min Act: -0.1700
Data Index: 124875 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9667. Min Range: -7.9667
Max Act: 7.1542. Min Act: -0.1700
Data Index: 1447382 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9667. Min Range: -7.9667
Max Act: 7.0917. Min Act: -0.1700
Data Index: 4007497 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9667. Min Range: -7.9667
Max Act: 7.0604. Min Act: -0.1700
Data Index: 4517719 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9667. Min Range: -7.9667
Max Act: 7.0292. Min Act: -0.1700
Data Index: 7900558 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9667. Min Range: -7.9667
Max Act: 7.0292. Min Act: -0.1700
Data Index: 2535838 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9667. Min Range: -7.9667
Max Act: 6.9979. Min Act: -0.1700
Data Index: 590893 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9667. Min Range: -7.9667
Max Act: 6.9979. Min Act: -0.1700
Data Index: 8587168 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9667. Min Range: -7.9667
Max Act: 6.9667. Min Act: -0.1700
Data Index: 8736856 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9667. Min Range: -7.9667
Max Act: 6.9979. Min Act: -0.1700
Data Index: 2951600 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9667. Min Range: -7.9667
Max Act: 6.9979. Min Act: -0.1700
Data Index: 4762625 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9667. Min Range: -7.9667
Max Act: 6.9667. Min Act: -0.1700
Data Index: 5378693 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9667. Min Range: -7.9667
Max Act: 6.9667. Min Act: -0.1700
Data Index: 6762772 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9667. Min Range: -7.9667
Max Act: 6.9354. Min Act: -0.1700
Data Index: 3376474 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9667. Min Range: -7.9667
Max Act: 6.9354. Min Act: -0.1700
Data Index: 2528406 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9667. Min Range: -7.9667
Max Act: 6.9667. Min Act: -0.1700
Data Index: 3372413 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19