Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1218. Min Range: -6.1218
Max Act: 6.1218. Min Act: -0.1700
Data Index: 5488446 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1218. Min Range: -6.1218
Max Act: 5.1530. Min Act: -0.1700
Data Index: 8276857 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1218. Min Range: -6.1218
Max Act: 5.1218. Min Act: -0.1700
Data Index: 4664319 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1218. Min Range: -6.1218
Max Act: 5.1218. Min Act: -0.1700
Data Index: 4875298 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1218. Min Range: -6.1218
Max Act: 5.0593. Min Act: -0.1700
Data Index: 4608715 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1218. Min Range: -6.1218
Max Act: 5.0280. Min Act: -0.1700
Data Index: 1264273 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1218. Min Range: -6.1218
Max Act: 5.0280. Min Act: -0.1700
Data Index: 5009781 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1218. Min Range: -6.1218
Max Act: 5.0280. Min Act: -0.1700
Data Index: 6348162 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1218. Min Range: -6.1218
Max Act: 5.0593. Min Act: -0.1700
Data Index: 7836181 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1218. Min Range: -6.1218
Max Act: 5.0280. Min Act: -0.1700
Data Index: 7934695 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1218. Min Range: -6.1218
Max Act: 4.9968. Min Act: -0.1700
Data Index: 4674469 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1218. Min Range: -6.1218
Max Act: 4.9968. Min Act: -0.1700
Data Index: 2005443 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1218. Min Range: -6.1218
Max Act: 4.9655. Min Act: -0.1700
Data Index: 3719135 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1218. Min Range: -6.1218
Max Act: 4.9655. Min Act: -0.1700
Data Index: 8472446 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1218. Min Range: -6.1218
Max Act: 4.9655. Min Act: -0.1700
Data Index: 2472391 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1218. Min Range: -6.1218
Max Act: 4.9655. Min Act: -0.1700
Data Index: 397617 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1218. Min Range: -6.1218
Max Act: 4.9343. Min Act: -0.1700
Data Index: 502152 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1218. Min Range: -6.1218
Max Act: 4.9343. Min Act: -0.1700
Data Index: 7218220 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1218. Min Range: -6.1218
Max Act: 4.9343. Min Act: -0.1700
Data Index: 911078 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1218. Min Range: -6.1218
Max Act: 4.9343. Min Act: -0.1700
Data Index: 7803414 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19