Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.5369. Min Act: -0.1700
Data Index: 2956499 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.4431. Min Act: -0.1700
Data Index: 5485625 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.3806. Min Act: -0.1700
Data Index: 8084899 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.3806. Min Act: -0.1700
Data Index: 4148517 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.3494. Min Act: -0.1700
Data Index: 8181566 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.3181. Min Act: -0.1700
Data Index: 1704091 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.3181. Min Act: -0.1700
Data Index: 2069982 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.2869. Min Act: -0.1700
Data Index: 2591123 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.2556. Min Act: -0.1700
Data Index: 7071655 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.2556. Min Act: -0.1700
Data Index: 979874 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.2556. Min Act: -0.1700
Data Index: 943669 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.2244. Min Act: -0.1700
Data Index: 2956498 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.2244. Min Act: -0.1700
Data Index: 943668 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.1931. Min Act: -0.1700
Data Index: 8010284 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.1931. Min Act: -0.1700
Data Index: 5221268 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.1931. Min Act: -0.1700
Data Index: 5700612 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.1306. Min Act: -0.1700
Data Index: 3780467 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.0681. Min Act: -0.1700
Data Index: 1114822 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.0369. Min Act: -0.1700
Data Index: 6266895 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5369. Min Range: -5.5369
Max Act: 5.0369. Min Act: -0.1700
Data Index: 4115010 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19