Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.5821. Min Act: -0.1700
Data Index: 2207034 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.5509. Min Act: -0.1700
Data Index: 5231035 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.5196. Min Act: -0.1700
Data Index: 1673131 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.4884. Min Act: -0.1700
Data Index: 8387419 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.4884. Min Act: -0.1700
Data Index: 4090081 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.4259. Min Act: -0.1700
Data Index: 4660290 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3946. Min Act: -0.1700
Data Index: 1631021 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.4571. Min Act: -0.1700
Data Index: 7543285 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.4259. Min Act: -0.1700
Data Index: 3389815 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3946. Min Act: -0.1700
Data Index: 5531613 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.4259. Min Act: -0.1700
Data Index: 3962050 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3946. Min Act: -0.1700
Data Index: 152720 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3946. Min Act: -0.1700
Data Index: 3685402 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3321. Min Act: -0.1700
Data Index: 7592147 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3634. Min Act: -0.1700
Data Index: 2872158 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3321. Min Act: -0.1700
Data Index: 911046 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3321. Min Act: -0.1700
Data Index: 5889890 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3321. Min Act: -0.1700
Data Index: 8778883 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3009. Min Act: -0.1700
Data Index: 1239183 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5821. Min Range: -5.5821
Max Act: 5.3009. Min Act: -0.1700
Data Index: 6528432 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19