Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.5134. Min Act: -0.1700
Data Index: 2875795 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.4509. Min Act: -0.1700
Data Index: 3550543 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.4509. Min Act: -0.1700
Data Index: 8603049 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3884. Min Act: -0.1700
Data Index: 2539251 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3884. Min Act: -0.1700
Data Index: 292742 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3884. Min Act: -0.1700
Data Index: 5757988 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 4361457 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 6841045 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 4036438 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.3259. Min Act: -0.1700
Data Index: 7585324 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.2634. Min Act: -0.1700
Data Index: 1838708 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.2634. Min Act: -0.1700
Data Index: 8594800 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1696. Min Act: -0.1700
Data Index: 7152353 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1696. Min Act: -0.1700
Data Index: 821648 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1384. Min Act: -0.1700
Data Index: 1370047 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1384. Min Act: -0.1700
Data Index: 3578317 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1071. Min Act: -0.1700
Data Index: 7779797 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1071. Min Act: -0.1700
Data Index: 2539241 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1071. Min Act: -0.1700
Data Index: 8226252 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5134. Min Range: -5.5134
Max Act: 5.1071. Min Act: -0.1700
Data Index: 7549961 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19