Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 965 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.5279. Min Act: -0.1700
Data Index: 2654809 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.5279. Min Act: -0.1700
Data Index: 7125412 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.4654. Min Act: -0.1700
Data Index: 3170615 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.4029. Min Act: -0.1700
Data Index: 3953289 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.4341. Min Act: -0.1700
Data Index: 1195313 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.4029. Min Act: -0.1700
Data Index: 6546109 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.4029. Min Act: -0.1700
Data Index: 714253 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.4029. Min Act: -0.1700
Data Index: 8703666 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.4029. Min Act: -0.1700
Data Index: 7163056 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.4029. Min Act: -0.1700
Data Index: 1842767 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.4029. Min Act: -0.1700
Data Index: 224248 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.3716. Min Act: -0.1700
Data Index: 95305 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.3716. Min Act: -0.1700
Data Index: 6052005 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.3716. Min Act: -0.1700
Data Index: 1354864 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.3716. Min Act: -0.1700
Data Index: 5506367 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.3716. Min Act: -0.1700
Data Index: 5250985 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.3404. Min Act: -0.1700
Data Index: 7125413 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.3716. Min Act: -0.1700
Data Index: 3660945 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.3091. Min Act: -0.1700
Data Index: 1415434 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.3404. Min Act: -0.1700
Data Index: 6116510 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19