Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.9202. Min Act: -0.1700
Data Index: 4669795 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.9043. Min Act: -0.1700
Data Index: 8297738 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.9202. Min Act: -0.1700
Data Index: 1285474 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.8567. Min Act: -0.1700
Data Index: 3123109 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.8249. Min Act: -0.1700
Data Index: 7058533 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.8249. Min Act: -0.1700
Data Index: 6357648 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.8249. Min Act: -0.1700
Data Index: 40800 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.8090. Min Act: -0.1700
Data Index: 5822763 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.8249. Min Act: -0.1700
Data Index: 4831880 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.7772. Min Act: -0.1700
Data Index: 7090795 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.7612. Min Act: -0.1700
Data Index: 731800 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.7772. Min Act: -0.1700
Data Index: 6250259 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.7772. Min Act: -0.1700
Data Index: 2615069 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.7931. Min Act: -0.1700
Data Index: 2105813 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.7453. Min Act: -0.1700
Data Index: 3001382 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.7453. Min Act: -0.1700
Data Index: 4334967 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.6653. Min Act: -0.1700
Data Index: 1585987 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.7453. Min Act: -0.1700
Data Index: 2560978 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.7293. Min Act: -0.1700
Data Index: 2369550 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9202. Min Range: -2.9202
Max Act: 2.7612. Min Act: -0.1700
Data Index: 2517659 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19