Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1368 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0107. Min Range: -7.0107
Max Act: 7.0107. Min Act: -0.1700
Data Index: 7731440 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.8544. Min Act: -0.1700
Data Index: 3001177 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.7607. Min Act: -0.1700
Data Index: 1153682 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.4482. Min Act: -0.1700
Data Index: 7855829 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.3544. Min Act: -0.1700
Data Index: 2497030 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.4169. Min Act: -0.1700
Data Index: 2187138 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.3544. Min Act: -0.1700
Data Index: 5508508 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.3232. Min Act: -0.1700
Data Index: 7351830 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.3544. Min Act: -0.1700
Data Index: 3507825 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.2919. Min Act: -0.1700
Data Index: 7343464 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.2607. Min Act: -0.1700
Data Index: 5460745 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.1982. Min Act: -0.1700
Data Index: 6915982 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.2294. Min Act: -0.1700
Data Index: 4585861 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.1982. Min Act: -0.1700
Data Index: 2625895 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.2607. Min Act: -0.1700
Data Index: 6009893 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.1982. Min Act: -0.1700
Data Index: 3569208 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.2294. Min Act: -0.1700
Data Index: 2421369 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.2607. Min Act: -0.1700
Data Index: 4630183 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.2294. Min Act: -0.1700
Data Index: 2971234 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0107. Min Range: -7.0107
Max Act: 6.1982. Min Act: -0.1700
Data Index: 3921839 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19