Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7989. Min Range: -5.7989
Max Act: 5.7989. Min Act: -0.1700
Data Index: 3861663 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7989. Min Range: -5.7989
Max Act: 5.2989. Min Act: -0.1700
Data Index: 5486618 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7989. Min Range: -5.7989
Max Act: 5.3302. Min Act: -0.1700
Data Index: 2222145 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7989. Min Range: -5.7989
Max Act: 5.2052. Min Act: -0.1700
Data Index: 4703138 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7989. Min Range: -5.7989
Max Act: 5.0802. Min Act: -0.1700
Data Index: 7868179 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7989. Min Range: -5.7989
Max Act: 5.0177. Min Act: -0.1700
Data Index: 7153291 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.9864. Min Act: -0.1700
Data Index: 6642519 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7989. Min Range: -5.7989
Max Act: 5.0177. Min Act: -0.1700
Data Index: 5751392 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.8927. Min Act: -0.1700
Data Index: 2970787 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.8614. Min Act: -0.1700
Data Index: 5914596 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.9239. Min Act: -0.1700
Data Index: 5949525 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.8927. Min Act: -0.1700
Data Index: 2721800 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.9239. Min Act: -0.1700
Data Index: 1164140 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.9239. Min Act: -0.1700
Data Index: 8121773 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.8614. Min Act: -0.1700
Data Index: 2813971 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.8614. Min Act: -0.1700
Data Index: 1899363 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.8302. Min Act: -0.1700
Data Index: 4743223 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.8927. Min Act: -0.1700
Data Index: 1583490 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.7052. Min Act: -0.1700
Data Index: 986233 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7989. Min Range: -5.7989
Max Act: 4.7052. Min Act: -0.1700
Data Index: 5674658 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19