Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4830 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.9209. Min Act: -0.1700
Data Index: 240984 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.9209. Min Act: -0.1700
Data Index: 4574171 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.8584. Min Act: -0.1700
Data Index: 6693317 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.7959. Min Act: -0.1700
Data Index: 885643 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.7959. Min Act: -0.1700
Data Index: 4571882 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.7022. Min Act: -0.1700
Data Index: 3445289 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.6397. Min Act: -0.1700
Data Index: 5514470 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.7022. Min Act: -0.1700
Data Index: 308548 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.6397. Min Act: -0.1700
Data Index: 4955259 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.6397. Min Act: -0.1700
Data Index: 232752 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.5772. Min Act: -0.1700
Data Index: 4408108 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.6084. Min Act: -0.1700
Data Index: 6399331 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.6084. Min Act: -0.1700
Data Index: 7915848 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.6084. Min Act: -0.1700
Data Index: 3349916 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.5772. Min Act: -0.1700
Data Index: 7653287 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.5772. Min Act: -0.1700
Data Index: 3998506 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.5459. Min Act: -0.1700
Data Index: 6009696 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.5459. Min Act: -0.1700
Data Index: 4214073 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.5772. Min Act: -0.1700
Data Index: 7392741 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9209. Min Range: -5.9209
Max Act: 5.5459. Min Act: -0.1700
Data Index: 4151770 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19