Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1388. Min Range: -7.1388
Max Act: 7.1388. Min Act: -0.1700
Data Index: 5848392 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.7638. Min Act: -0.1700
Data Index: 2770666 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.7325. Min Act: -0.1700
Data Index: 1094992 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.6700. Min Act: -0.1700
Data Index: 8663236 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.5763. Min Act: -0.1700
Data Index: 4273215 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.5450. Min Act: -0.1700
Data Index: 8231766 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.5138. Min Act: -0.1700
Data Index: 2079872 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.4825. Min Act: -0.1700
Data Index: 8525636 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.4825. Min Act: -0.1700
Data Index: 736768 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.4825. Min Act: -0.1700
Data Index: 395762 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.4513. Min Act: -0.1700
Data Index: 5925949 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.4200. Min Act: -0.1700
Data Index: 8679862 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.4513. Min Act: -0.1700
Data Index: 3799353 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.3888. Min Act: -0.1700
Data Index: 8309673 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.3575. Min Act: -0.1700
Data Index: 4214484 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.3575. Min Act: -0.1700
Data Index: 5816320 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.3263. Min Act: -0.1700
Data Index: 6282544 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.3263. Min Act: -0.1700
Data Index: 643623 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.3263. Min Act: -0.1700
Data Index: 7534015 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1388. Min Range: -7.1388
Max Act: 6.3263. Min Act: -0.1700
Data Index: 7410055 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19