Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4356 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6329. Min Range: -8.6329
Max Act: 8.6329. Min Act: -0.1700
Data Index: 5659590 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6329. Min Range: -8.6329
Max Act: 8.3829. Min Act: -0.1700
Data Index: 7261301 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6329. Min Range: -8.6329
Max Act: 8.2579. Min Act: -0.1700
Data Index: 7261303 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6329. Min Range: -8.6329
Max Act: 8.0704. Min Act: -0.1700
Data Index: 4365566 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6329. Min Range: -8.6329
Max Act: 8.0079. Min Act: -0.1700
Data Index: 7570751 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.9454. Min Act: -0.1700
Data Index: 7824448 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6329. Min Range: -8.6329
Max Act: 8.0079. Min Act: -0.1700
Data Index: 8646737 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.9454. Min Act: -0.1700
Data Index: 5847797 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.8204. Min Act: -0.1700
Data Index: 222616 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.8204. Min Act: -0.1700
Data Index: 4294215 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.8204. Min Act: -0.1700
Data Index: 6277138 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.8204. Min Act: -0.1700
Data Index: 5367932 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.8204. Min Act: -0.1700
Data Index: 7640641 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.8204. Min Act: -0.1700
Data Index: 358525 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.8204. Min Act: -0.1700
Data Index: 3065341 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.7579. Min Act: -0.1700
Data Index: 4627831 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.7579. Min Act: -0.1700
Data Index: 6170558 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.7579. Min Act: -0.1700
Data Index: 1396755 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.7579. Min Act: -0.1700
Data Index: 6939208 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6329. Min Range: -8.6329
Max Act: 7.8204. Min Act: -0.1700
Data Index: 5266011 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19