Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0397. Min Range: -8.0397
Max Act: 8.0397. Min Act: -0.1700
Data Index: 8280322 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.9772. Min Act: -0.1700
Data Index: 2623911 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.9147. Min Act: -0.1700
Data Index: 2766990 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.8522. Min Act: -0.1700
Data Index: 2450318 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.7897. Min Act: -0.1700
Data Index: 3878789 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.7584. Min Act: -0.1700
Data Index: 3046946 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.7584. Min Act: -0.1700
Data Index: 5183539 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.7272. Min Act: -0.1700
Data Index: 7547163 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6959. Min Act: -0.1700
Data Index: 7793435 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6959. Min Act: -0.1700
Data Index: 3631467 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.7272. Min Act: -0.1700
Data Index: 1841226 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6959. Min Act: -0.1700
Data Index: 3718911 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6959. Min Act: -0.1700
Data Index: 3367530 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6959. Min Act: -0.1700
Data Index: 1186179 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6647. Min Act: -0.1700
Data Index: 8526562 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6334. Min Act: -0.1700
Data Index: 8693876 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6022. Min Act: -0.1700
Data Index: 6153175 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6022. Min Act: -0.1700
Data Index: 195333 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6022. Min Act: -0.1700
Data Index: 2363992 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0397. Min Range: -8.0397
Max Act: 7.6022. Min Act: -0.1700
Data Index: 8177723 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19