Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.4583. Min Act: -0.1700
Data Index: 6879095 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.4270. Min Act: -0.1700
Data Index: 4484715 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.4270. Min Act: -0.1700
Data Index: 897289 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.3333. Min Act: -0.1700
Data Index: 1155249 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.3645. Min Act: -0.1700
Data Index: 7100716 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.3020. Min Act: -0.1700
Data Index: 1803427 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.2708. Min Act: -0.1700
Data Index: 3490343 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.2395. Min Act: -0.1700
Data Index: 4024219 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.2083. Min Act: -0.1700
Data Index: 414627 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.2395. Min Act: -0.1700
Data Index: 1580336 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.1770. Min Act: -0.1700
Data Index: 5196748 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.1770. Min Act: -0.1700
Data Index: 8807299 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.1770. Min Act: -0.1700
Data Index: 7190062 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.1458. Min Act: -0.1700
Data Index: 6885135 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.0833. Min Act: -0.1700
Data Index: 684138 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.1145. Min Act: -0.1700
Data Index: 2748973 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.0833. Min Act: -0.1700
Data Index: 1473363 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.1145. Min Act: -0.1700
Data Index: 6809228 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.1145. Min Act: -0.1700
Data Index: 13524 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4583. Min Range: -5.4583
Max Act: 5.0833. Min Act: -0.1700
Data Index: 2211632 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19