Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3335 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.3079. Min Act: -0.1699
Data Index: 3457713 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.2141. Min Act: -0.1700
Data Index: 1089241 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.2141. Min Act: -0.1700
Data Index: 6101382 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.2141. Min Act: -0.1699
Data Index: 151130 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.1829. Min Act: -0.1700
Data Index: 2628394 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.1516. Min Act: -0.1700
Data Index: 4648987 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.1204. Min Act: -0.1700
Data Index: 5297480 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.1204. Min Act: -0.1700
Data Index: 869029 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.1204. Min Act: -0.1700
Data Index: 4726150 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.0266. Min Act: -0.1700
Data Index: 707637 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.0579. Min Act: -0.1700
Data Index: 5801234 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.0891. Min Act: -0.1700
Data Index: 3948690 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.0266. Min Act: -0.1700
Data Index: 8564337 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.0266. Min Act: -0.1700
Data Index: 5845714 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3079. Min Range: -5.3079
Max Act: 5.0579. Min Act: -0.1700
Data Index: 1124188 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3079. Min Range: -5.3079
Max Act: 4.9954. Min Act: -0.1700
Data Index: 687606 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3079. Min Range: -5.3079
Max Act: 4.9954. Min Act: -0.1700
Data Index: 2054525 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3079. Min Range: -5.3079
Max Act: 4.9954. Min Act: -0.1700
Data Index: 2598517 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3079. Min Range: -5.3079
Max Act: 4.9641. Min Act: -0.1700
Data Index: 619717 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3079. Min Range: -5.3079
Max Act: 4.9954. Min Act: -0.1700
Data Index: 337288 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19