Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 352 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.7346. Min Act: -0.1700
Data Index: 4501347 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.7186. Min Act: -0.1700
Data Index: 5496637 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.6545. Min Act: -0.1700
Data Index: 3817410 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.6224. Min Act: -0.1700
Data Index: 1023320 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.6224. Min Act: -0.1700
Data Index: 5496648 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.6224. Min Act: -0.1700
Data Index: 5907439 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.5902. Min Act: -0.1700
Data Index: 944137 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.5902. Min Act: -0.1700
Data Index: 2194731 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.5418. Min Act: -0.1700
Data Index: 3039397 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.5741. Min Act: -0.1700
Data Index: 6158098 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.5418. Min Act: -0.1700
Data Index: 5736638 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.5257. Min Act: -0.1700
Data Index: 4501346 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.5418. Min Act: -0.1700
Data Index: 4770053 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.5418. Min Act: -0.1700
Data Index: 8326347 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.4771. Min Act: -0.1700
Data Index: 7650851 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.4933. Min Act: -0.1700
Data Index: 812509 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.4933. Min Act: -0.1700
Data Index: 4656026 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.4771. Min Act: -0.1700
Data Index: 6088800 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.4933. Min Act: -0.1700
Data Index: 5755521 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7346. Min Range: -2.7346
Max Act: 2.4608. Min Act: -0.1700
Data Index: 6899701 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19