Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1990 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.1602. Min Act: -0.1700
Data Index: 643719 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.1290. Min Act: -0.1700
Data Index: 884971 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.1290. Min Act: -0.1700
Data Index: 4519403 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0977. Min Act: -0.1700
Data Index: 6801956 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0665. Min Act: -0.1700
Data Index: 553298 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 3832835 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 4576234 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 443910 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 3972618 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 6188228 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 6804962 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 8754679 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0040. Min Act: -0.1700
Data Index: 5334808 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0040. Min Act: -0.1700
Data Index: 1296212 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0352. Min Act: -0.1700
Data Index: 8439574 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0040. Min Act: -0.1700
Data Index: 8406050 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0040. Min Act: -0.1700
Data Index: 6246686 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1602. Min Range: -5.1602
Max Act: 4.9727. Min Act: -0.1700
Data Index: 8344573 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1602. Min Range: -5.1602
Max Act: 5.0040. Min Act: -0.1700
Data Index: 479806 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1602. Min Range: -5.1602
Max Act: 4.9727. Min Act: -0.1700
Data Index: 1470693 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19