Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1811 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.5065. Min Act: -0.1700
Data Index: 538712 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.5377. Min Act: -0.1700
Data Index: 5496851 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.4440. Min Act: -0.1700
Data Index: 497172 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.4127. Min Act: -0.1700
Data Index: 3858562 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.3190. Min Act: -0.1700
Data Index: 6348585 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.3190. Min Act: -0.1700
Data Index: 5656011 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.3190. Min Act: -0.1700
Data Index: 5512789 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.3190. Min Act: -0.1700
Data Index: 4609398 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.2877. Min Act: -0.1700
Data Index: 7545996 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.2565. Min Act: -0.1700
Data Index: 3051516 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.2877. Min Act: -0.1700
Data Index: 496386 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.2565. Min Act: -0.1700
Data Index: 5397782 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.2252. Min Act: -0.1700
Data Index: 7394034 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.2252. Min Act: -0.1700
Data Index: 2370472 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.1940. Min Act: -0.1700
Data Index: 5914437 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.1940. Min Act: -0.1700
Data Index: 5656017 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.2252. Min Act: -0.1700
Data Index: 195779 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.2252. Min Act: -0.1700
Data Index: 4592158 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.1627. Min Act: -0.1700
Data Index: 5035826 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5377. Min Range: -6.5377
Max Act: 6.1627. Min Act: -0.1700
Data Index: 6844261 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19