Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4161. Min Range: -6.4161
Max Act: 6.4161. Min Act: -0.1700
Data Index: 8041442 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4161. Min Range: -6.4161
Max Act: 6.2286. Min Act: -0.1700
Data Index: 4476026 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.9786. Min Act: -0.1700
Data Index: 620596 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4161. Min Range: -6.4161
Max Act: 6.0098. Min Act: -0.1700
Data Index: 2803074 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.9786. Min Act: -0.1700
Data Index: 4232317 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.9786. Min Act: -0.1700
Data Index: 1486221 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8848. Min Act: -0.1700
Data Index: 4934671 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8223. Min Act: -0.1700
Data Index: 2579503 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8223. Min Act: -0.1700
Data Index: 6031106 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.7911. Min Act: -0.1700
Data Index: 7573890 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.7911. Min Act: -0.1700
Data Index: 5642318 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.8223. Min Act: -0.1700
Data Index: 6813958 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.7598. Min Act: -0.1700
Data Index: 3709189 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.7286. Min Act: -0.1700
Data Index: 1313529 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.7598. Min Act: -0.1700
Data Index: 3714794 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.7911. Min Act: -0.1700
Data Index: 7839904 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.6661. Min Act: -0.1700
Data Index: 4297190 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.6348. Min Act: -0.1700
Data Index: 5898887 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.6661. Min Act: -0.1700
Data Index: 87957 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4161. Min Range: -6.4161
Max Act: 5.6661. Min Act: -0.1700
Data Index: 7570802 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19