Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0560. Min Range: -7.0560
Max Act: 7.0560. Min Act: -0.1700
Data Index: 8219142 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.8685. Min Act: -0.1700
Data Index: 8025187 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.6498. Min Act: -0.1700
Data Index: 6826004 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.6185. Min Act: -0.1700
Data Index: 8025190 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.4935. Min Act: -0.1700
Data Index: 8025185 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.3998. Min Act: -0.1700
Data Index: 8219139 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.3685. Min Act: -0.1700
Data Index: 4414598 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.3373. Min Act: -0.1700
Data Index: 5330648 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.3373. Min Act: -0.1700
Data Index: 4452901 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.3373. Min Act: -0.1700
Data Index: 2562763 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.3060. Min Act: -0.1700
Data Index: 437899 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.2748. Min Act: -0.1700
Data Index: 937486 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.3060. Min Act: -0.1700
Data Index: 6413389 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.2435. Min Act: -0.1700
Data Index: 3075859 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.2123. Min Act: -0.1700
Data Index: 6648688 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.2123. Min Act: -0.1700
Data Index: 4649631 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.2435. Min Act: -0.1700
Data Index: 8219140 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.2123. Min Act: -0.1700
Data Index: 3270119 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.1810. Min Act: -0.1700
Data Index: 8180346 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0560. Min Range: -7.0560
Max Act: 6.1810. Min Act: -0.1700
Data Index: 652646 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19