Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.4130. Min Act: -0.1700
Data Index: 2191590 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.3505. Min Act: -0.1700
Data Index: 298805 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.2880. Min Act: -0.1700
Data Index: 768209 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.2880. Min Act: -0.1700
Data Index: 2833519 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.2568. Min Act: -0.1700
Data Index: 3677461 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.3193. Min Act: -0.1700
Data Index: 7610677 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.2568. Min Act: -0.1700
Data Index: 8088336 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.2568. Min Act: -0.1700
Data Index: 4658360 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.1943. Min Act: -0.1700
Data Index: 1473858 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.2255. Min Act: -0.1700
Data Index: 7716837 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.2568. Min Act: -0.1700
Data Index: 7514493 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.1943. Min Act: -0.1700
Data Index: 3353767 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.2568. Min Act: -0.1700
Data Index: 3669145 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.1943. Min Act: -0.1700
Data Index: 4910244 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.1943. Min Act: -0.1700
Data Index: 1833506 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.2568. Min Act: -0.1700
Data Index: 8088332 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.2255. Min Act: -0.1700
Data Index: 8592545 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.1943. Min Act: -0.1700
Data Index: 4465243 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.1318. Min Act: -0.1698
Data Index: 3802753 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4130. Min Range: -6.4130
Max Act: 6.0693. Min Act: -0.1700
Data Index: 3438452 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19