Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1419 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4479. Min Range: -6.4479
Max Act: 6.4479. Min Act: -0.1700
Data Index: 7376556 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4479. Min Range: -6.4479
Max Act: 6.1041. Min Act: -0.1700
Data Index: 8711735 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4479. Min Range: -6.4479
Max Act: 6.0416. Min Act: -0.1700
Data Index: 8582554 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4479. Min Range: -6.4479
Max Act: 6.0729. Min Act: -0.1700
Data Index: 8451208 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4479. Min Range: -6.4479
Max Act: 6.0416. Min Act: -0.1700
Data Index: 6556786 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4479. Min Range: -6.4479
Max Act: 6.0104. Min Act: -0.1700
Data Index: 1448100 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4479. Min Range: -6.4479
Max Act: 6.0104. Min Act: -0.1700
Data Index: 7283976 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9791. Min Act: -0.1700
Data Index: 5815388 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4479. Min Range: -6.4479
Max Act: 6.0104. Min Act: -0.1700
Data Index: 6792763 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4479. Min Range: -6.4479
Max Act: 6.0104. Min Act: -0.1700
Data Index: 7788682 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9479. Min Act: -0.1700
Data Index: 6983977 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9791. Min Act: -0.1700
Data Index: 6678934 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9166. Min Act: -0.1700
Data Index: 7288940 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9479. Min Act: -0.1700
Data Index: 2814397 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9166. Min Act: -0.1700
Data Index: 7829094 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9479. Min Act: -0.1700
Data Index: 232481 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9166. Min Act: -0.1700
Data Index: 7187738 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9166. Min Act: -0.1700
Data Index: 7779892 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9166. Min Act: -0.1700
Data Index: 5675777 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4479. Min Range: -6.4479
Max Act: 5.9166. Min Act: -0.1700
Data Index: 2471112 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19