Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.8305. Min Act: -0.1700
Data Index: 3846898 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.7992. Min Act: -0.1700
Data Index: 6192100 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.7367. Min Act: -0.1700
Data Index: 3248525 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.7367. Min Act: -0.1700
Data Index: 234896 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.7367. Min Act: -0.1700
Data Index: 4261043 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.6742. Min Act: -0.1700
Data Index: 6003816 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.7055. Min Act: -0.1700
Data Index: 2690592 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.6430. Min Act: -0.1700
Data Index: 1104960 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.6742. Min Act: -0.1700
Data Index: 3537077 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.6117. Min Act: -0.1700
Data Index: 2313631 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.6117. Min Act: -0.1700
Data Index: 2017137 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.6117. Min Act: -0.1700
Data Index: 7014379 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.6117. Min Act: -0.1700
Data Index: 7317562 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.5805. Min Act: -0.1700
Data Index: 185317 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.6430. Min Act: -0.1700
Data Index: 3710778 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.5805. Min Act: -0.1700
Data Index: 4666183 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.4867. Min Act: -0.1700
Data Index: 2329991 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.5180. Min Act: -0.1700
Data Index: 2127577 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.4867. Min Act: -0.1700
Data Index: 6166149 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8305. Min Range: -5.8305
Max Act: 5.4867. Min Act: -0.1700
Data Index: 6214565 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19