Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3978 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0480. Min Range: -3.0480
Max Act: 3.0480. Min Act: -0.1700
Data Index: 2381682 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0480. Min Range: -3.0480
Max Act: 3.0323. Min Act: -0.1700
Data Index: 8651235 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0480. Min Range: -3.0480
Max Act: 3.0323. Min Act: -0.1700
Data Index: 7822334 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0480. Min Range: -3.0480
Max Act: 3.0165. Min Act: -0.1700
Data Index: 1832914 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0480. Min Range: -3.0480
Max Act: 3.0007. Min Act: -0.1700
Data Index: 3304842 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0480. Min Range: -3.0480
Max Act: 3.0165. Min Act: -0.1700
Data Index: 5229729 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0480. Min Range: -3.0480
Max Act: 3.0007. Min Act: -0.1700
Data Index: 4977689 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0480. Min Range: -3.0480
Max Act: 3.0007. Min Act: -0.1700
Data Index: 2641984 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0480. Min Range: -3.0480
Max Act: 3.0007. Min Act: -0.1700
Data Index: 710203 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9849. Min Act: -0.1700
Data Index: 8708923 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9849. Min Act: -0.1700
Data Index: 2658131 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9690. Min Act: -0.1700
Data Index: 8444920 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9690. Min Act: -0.1700
Data Index: 4234530 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9690. Min Act: -0.1700
Data Index: 5481234 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9690. Min Act: -0.1700
Data Index: 6158257 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9690. Min Act: -0.1700
Data Index: 3599039 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9690. Min Act: -0.1700
Data Index: 52115 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9532. Min Act: -0.1700
Data Index: 5993645 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9532. Min Act: -0.1700
Data Index: 559296 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0480. Min Range: -3.0480
Max Act: 2.9532. Min Act: -0.1700
Data Index: 8565025 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19