Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.5829. Min Act: -0.1700
Data Index: 3882650 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.5517. Min Act: -0.1700
Data Index: 6584916 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.6142. Min Act: -0.1700
Data Index: 8499522 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.6142. Min Act: -0.1700
Data Index: 692782 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.4892. Min Act: -0.1700
Data Index: 6924162 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.5204. Min Act: -0.1700
Data Index: 7177140 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.4892. Min Act: -0.1700
Data Index: 7737311 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.4267. Min Act: -0.1700
Data Index: 3288459 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.4579. Min Act: -0.1700
Data Index: 1868604 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.3954. Min Act: -0.1700
Data Index: 8149658 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.3954. Min Act: -0.1700
Data Index: 49423 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.3954. Min Act: -0.1700
Data Index: 3066954 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.3642. Min Act: -0.1700
Data Index: 1499091 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.3642. Min Act: -0.1700
Data Index: 6207124 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.3954. Min Act: -0.1700
Data Index: 5242341 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.2704. Min Act: -0.1700
Data Index: 4726850 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.2704. Min Act: -0.1700
Data Index: 4016027 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.2704. Min Act: -0.1700
Data Index: 5315372 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.2392. Min Act: -0.1700
Data Index: 5110810 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6142. Min Range: -6.6142
Max Act: 6.2079. Min Act: -0.1700
Data Index: 5260338 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19