Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2188 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.3159. Min Act: -0.1700
Data Index: 5505866 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2335. Min Act: -0.1700
Data Index: 3494478 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2335. Min Act: -0.1700
Data Index: 2070940 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2169. Min Act: -0.1700
Data Index: 2664831 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1837. Min Act: -0.1700
Data Index: 3434792 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1837. Min Act: -0.1700
Data Index: 5771408 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2003. Min Act: -0.1700
Data Index: 1179152 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1837. Min Act: -0.1700
Data Index: 361585 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.2003. Min Act: -0.1700
Data Index: 1904309 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1671. Min Act: -0.1700
Data Index: 3815281 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1671. Min Act: -0.1700
Data Index: 2086910 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1338. Min Act: -0.1700
Data Index: 356227 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1837. Min Act: -0.1700
Data Index: 4354820 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1671. Min Act: -0.1700
Data Index: 8261406 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1671. Min Act: -0.1700
Data Index: 2353975 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1504. Min Act: -0.1700
Data Index: 7277146 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1671. Min Act: -0.1700
Data Index: 3773479 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1671. Min Act: -0.1700
Data Index: 4150510 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1504. Min Act: -0.1700
Data Index: 4878463 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3159. Min Range: -2.3159
Max Act: 2.1671. Min Act: -0.1700
Data Index: 6643694 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19