Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4293 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2983. Min Range: -8.2983
Max Act: 8.2983. Min Act: -0.1700
Data Index: 2880889 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2983. Min Range: -8.2983
Max Act: 8.2358. Min Act: -0.1700
Data Index: 4531885 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2983. Min Range: -8.2983
Max Act: 8.2983. Min Act: -0.1700
Data Index: 6878203 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2983. Min Range: -8.2983
Max Act: 8.2358. Min Act: -0.1700
Data Index: 3196601 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2983. Min Range: -8.2983
Max Act: 8.0796. Min Act: -0.1700
Data Index: 5830867 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.9858. Min Act: -0.1700
Data Index: 6330481 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.9233. Min Act: -0.1700
Data Index: 7021919 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.8608. Min Act: -0.1700
Data Index: 2036986 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.8608. Min Act: -0.1700
Data Index: 7227811 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.8608. Min Act: -0.1700
Data Index: 8219721 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.7983. Min Act: -0.1700
Data Index: 4210259 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.7671. Min Act: -0.1700
Data Index: 4497437 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.7358. Min Act: -0.1700
Data Index: 7654458 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.7046. Min Act: -0.1700
Data Index: 6787264 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.6733. Min Act: -0.1700
Data Index: 3410486 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.6733. Min Act: -0.1700
Data Index: 499629 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.6733. Min Act: -0.1700
Data Index: 27051 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.6733. Min Act: -0.1700
Data Index: 3283344 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.6733. Min Act: -0.1700
Data Index: 3024032 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2983. Min Range: -8.2983
Max Act: 7.7046. Min Act: -0.1700
Data Index: 5503004 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19