Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2863 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3405. Min Range: -7.3405
Max Act: 7.3405. Min Act: -0.1700
Data Index: 2376614 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3405. Min Range: -7.3405
Max Act: 7.2155. Min Act: -0.1700
Data Index: 6741291 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3405. Min Range: -7.3405
Max Act: 7.0592. Min Act: -0.1700
Data Index: 58990 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3405. Min Range: -7.3405
Max Act: 7.0280. Min Act: -0.1700
Data Index: 2147346 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.9030. Min Act: -0.1700
Data Index: 6122831 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.9030. Min Act: -0.1700
Data Index: 6206394 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.8092. Min Act: -0.1700
Data Index: 886216 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.7780. Min Act: -0.1700
Data Index: 4303596 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.7467. Min Act: -0.1700
Data Index: 3682268 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.6842. Min Act: -0.1700
Data Index: 845145 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.6217. Min Act: -0.1700
Data Index: 2453026 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.6217. Min Act: -0.1700
Data Index: 373074 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.5905. Min Act: -0.1700
Data Index: 227626 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.5905. Min Act: -0.1700
Data Index: 7199720 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.5592. Min Act: -0.1700
Data Index: 1830225 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.5592. Min Act: -0.1700
Data Index: 6147178 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.5905. Min Act: -0.1700
Data Index: 5672012 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.4967. Min Act: -0.1700
Data Index: 3460829 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.4967. Min Act: -0.1700
Data Index: 5132211 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3405. Min Range: -7.3405
Max Act: 6.4655. Min Act: -0.1700
Data Index: 2108682 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19