Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3178 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0520. Min Range: -8.0520
Max Act: 8.0520. Min Act: -0.1700
Data Index: 6682861 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0520. Min Range: -8.0520
Max Act: 8.0520. Min Act: -0.1700
Data Index: 7391338 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.9270. Min Act: -0.1700
Data Index: 3641569 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.9270. Min Act: -0.1700
Data Index: 1905202 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.8645. Min Act: -0.1700
Data Index: 4778293 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.8020. Min Act: -0.1700
Data Index: 7884575 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.6770. Min Act: -0.1700
Data Index: 7631227 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.5832. Min Act: -0.1700
Data Index: 2283114 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.5520. Min Act: -0.1700
Data Index: 3047916 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.5207. Min Act: -0.1700
Data Index: 626080 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.5207. Min Act: -0.1700
Data Index: 329671 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.4895. Min Act: -0.1700
Data Index: 3869540 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.3957. Min Act: -0.1700
Data Index: 7793717 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.3957. Min Act: -0.1700
Data Index: 5387040 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.3332. Min Act: -0.1700
Data Index: 8012458 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.3020. Min Act: -0.1700
Data Index: 7032712 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.3332. Min Act: -0.1700
Data Index: 491970 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.3645. Min Act: -0.1700
Data Index: 2943647 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.3020. Min Act: -0.1700
Data Index: 7578489 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0520. Min Range: -8.0520
Max Act: 7.3020. Min Act: -0.1700
Data Index: 3061560 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19