Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5052 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.7161. Min Act: -0.1700
Data Index: 8559741 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.7161. Min Act: -0.1700
Data Index: 7340554 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.7161. Min Act: -0.1700
Data Index: 422371 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.6848. Min Act: -0.1700
Data Index: 333023 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.6536. Min Act: -0.1700
Data Index: 8025505 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.6536. Min Act: -0.1700
Data Index: 6112096 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.6536. Min Act: -0.1700
Data Index: 5580961 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.6223. Min Act: -0.1700
Data Index: 1318443 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.5911. Min Act: -0.1700
Data Index: 5957558 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.5911. Min Act: -0.1700
Data Index: 1716729 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.5598. Min Act: -0.1700
Data Index: 3461227 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.5286. Min Act: -0.1700
Data Index: 6040556 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.4973. Min Act: -0.1700
Data Index: 1705138 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.5286. Min Act: -0.1700
Data Index: 5861347 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.5286. Min Act: -0.1700
Data Index: 4003374 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.5286. Min Act: -0.1700
Data Index: 2425963 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.4973. Min Act: -0.1700
Data Index: 4803350 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.4973. Min Act: -0.1700
Data Index: 2074063 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.4973. Min Act: -0.1700
Data Index: 2139105 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7161. Min Range: -4.7161
Max Act: 4.4973. Min Act: -0.1700
Data Index: 3708734 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19