Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2241 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5848. Min Range: -9.5848
Max Act: 9.5848. Min Act: -0.1700
Data Index: 1425970 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5848. Min Range: -9.5848
Max Act: 9.2098. Min Act: -0.1700
Data Index: 7896661 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5848. Min Range: -9.5848
Max Act: 9.2098. Min Act: -0.1700
Data Index: 3915165 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5848. Min Range: -9.5848
Max Act: 9.2098. Min Act: -0.1700
Data Index: 7577896 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5848. Min Range: -9.5848
Max Act: 9.0223. Min Act: -0.1700
Data Index: 4143127 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5848. Min Range: -9.5848
Max Act: 9.0223. Min Act: -0.1700
Data Index: 8484502 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.9598. Min Act: -0.1700
Data Index: 1584556 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.9598. Min Act: -0.1700
Data Index: 7786976 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.8973. Min Act: -0.1700
Data Index: 1412926 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.8973. Min Act: -0.1700
Data Index: 6706583 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.8973. Min Act: -0.1700
Data Index: 3227205 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.8348. Min Act: -0.1700
Data Index: 1459106 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.8348. Min Act: -0.1700
Data Index: 3768316 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.8348. Min Act: -0.1700
Data Index: 1145599 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.8348. Min Act: -0.1700
Data Index: 2924822 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.7723. Min Act: -0.1700
Data Index: 8325404 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.7723. Min Act: -0.1700
Data Index: 1897541 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.7723. Min Act: -0.1700
Data Index: 641561 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.7723. Min Act: -0.1700
Data Index: 7806334 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5848. Min Range: -9.5848
Max Act: 8.7098. Min Act: -0.1700
Data Index: 72216 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19