Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5688 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.9132. Min Act: -0.1700
Data Index: 3506658 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.7412. Min Act: -0.1700
Data Index: 5113019 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.7099. Min Act: -0.1700
Data Index: 3383920 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.6004. Min Act: -0.1700
Data Index: 1395978 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.6160. Min Act: -0.1700
Data Index: 2256856 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.5847. Min Act: -0.1700
Data Index: 5626719 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.5691. Min Act: -0.1700
Data Index: 8701522 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.5691. Min Act: -0.1700
Data Index: 2892466 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.5534. Min Act: -0.1700
Data Index: 6477048 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.5221. Min Act: -0.1700
Data Index: 6568705 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.5064. Min Act: -0.1700
Data Index: 2375526 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.5064. Min Act: -0.1700
Data Index: 4261206 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.5064. Min Act: -0.1700
Data Index: 3433700 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.5064. Min Act: -0.1700
Data Index: 4704047 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.4908. Min Act: -0.1700
Data Index: 2671423 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.4594. Min Act: -0.1700
Data Index: 2167777 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.4594. Min Act: -0.1700
Data Index: 7156965 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.4751. Min Act: -0.1700
Data Index: 7973908 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.4594. Min Act: -0.1700
Data Index: 5351465 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9132. Min Range: -3.9132
Max Act: 3.4751. Min Act: -0.1700
Data Index: 2262125 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19