Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3182 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.3441. Min Act: -0.1700
Data Index: 1211308 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.3441. Min Act: -0.1700
Data Index: 1364415 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2816. Min Act: -0.1700
Data Index: 1429027 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2816. Min Act: -0.1700
Data Index: 535247 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2503. Min Act: -0.1700
Data Index: 3107502 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2503. Min Act: -0.1700
Data Index: 372671 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2191. Min Act: -0.1700
Data Index: 8069913 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2816. Min Act: -0.1700
Data Index: 7211501 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2816. Min Act: -0.1700
Data Index: 4784389 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2503. Min Act: -0.1700
Data Index: 4610960 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.1878. Min Act: -0.1700
Data Index: 560256 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2191. Min Act: -0.1700
Data Index: 6389884 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2191. Min Act: -0.1700
Data Index: 2267429 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.1878. Min Act: -0.1700
Data Index: 6853109 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2191. Min Act: -0.1700
Data Index: 8222528 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.2191. Min Act: -0.1700
Data Index: 6793832 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.1878. Min Act: -0.1700
Data Index: 3894684 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.1878. Min Act: -0.1700
Data Index: 3724682 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.1566. Min Act: -0.1700
Data Index: 4619078 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3441. Min Range: -4.3441
Max Act: 4.1878. Min Act: -0.1700
Data Index: 5106797 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19