Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1052 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.7172. Min Act: -0.1700
Data Index: 6884405 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.6547. Min Act: -0.1700
Data Index: 5107687 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.6547. Min Act: -0.1700
Data Index: 6719612 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.6235. Min Act: -0.1700
Data Index: 8802026 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5610. Min Act: -0.1700
Data Index: 411446 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.6235. Min Act: -0.1700
Data Index: 1050185 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5922. Min Act: -0.1700
Data Index: 7185141 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.6235. Min Act: -0.1699
Data Index: 6721422 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.6235. Min Act: -0.1699
Data Index: 4241857 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5922. Min Act: -0.1700
Data Index: 5963417 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5922. Min Act: -0.1700
Data Index: 614154 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5922. Min Act: -0.1700
Data Index: 6428869 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5610. Min Act: -0.1700
Data Index: 238257 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5922. Min Act: -0.1699
Data Index: 3312346 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5610. Min Act: -0.1700
Data Index: 25439 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5610. Min Act: -0.1700
Data Index: 3292243 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5610. Min Act: -0.1700
Data Index: 3183759 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5297. Min Act: -0.1700
Data Index: 396760 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5610. Min Act: -0.1700
Data Index: 1450907 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7172. Min Range: -6.7172
Max Act: 6.5610. Min Act: -0.1700
Data Index: 351340 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19