Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.8046. Min Act: -0.1700
Data Index: 2921561 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.8202. Min Act: -0.1700
Data Index: 2540957 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.8046. Min Act: -0.1700
Data Index: 4856212 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.7577. Min Act: -0.1700
Data Index: 4429544 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.6795. Min Act: -0.1700
Data Index: 8041563 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.6638. Min Act: -0.1700
Data Index: 1183540 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.6482. Min Act: -0.1700
Data Index: 5014863 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.6325. Min Act: -0.1700
Data Index: 518727 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.6325. Min Act: -0.1700
Data Index: 4248054 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.6012. Min Act: -0.1700
Data Index: 6343486 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.6012. Min Act: -0.1700
Data Index: 3000797 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.5856. Min Act: -0.1700
Data Index: 7295539 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.5699. Min Act: -0.1700
Data Index: 7813455 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.5543. Min Act: -0.1700
Data Index: 847864 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.5543. Min Act: -0.1700
Data Index: 6958327 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.5543. Min Act: -0.1700
Data Index: 7313585 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.5543. Min Act: -0.1700
Data Index: 2424516 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.5543. Min Act: -0.1700
Data Index: 2258419 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.5386. Min Act: -0.1700
Data Index: 1350254 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8202. Min Range: -3.8202
Max Act: 3.5386. Min Act: -0.1700
Data Index: 5356272 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19