Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.7599. Min Act: -0.1700
Data Index: 4964448 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.7599. Min Act: -0.1700
Data Index: 788962 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.6974. Min Act: -0.1700
Data Index: 955184 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.6036. Min Act: -0.1700
Data Index: 2852145 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.5411. Min Act: -0.1700
Data Index: 7603794 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.6036. Min Act: -0.1700
Data Index: 8218165 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.5099. Min Act: -0.1700
Data Index: 2137282 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.4474. Min Act: -0.1700
Data Index: 1422688 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.4161. Min Act: -0.1700
Data Index: 743312 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.3849. Min Act: -0.1700
Data Index: 4765824 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.2911. Min Act: -0.1700
Data Index: 1422691 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.3224. Min Act: -0.1700
Data Index: 6059315 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.3224. Min Act: -0.1700
Data Index: 7228022 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.2911. Min Act: -0.1700
Data Index: 4133050 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.3224. Min Act: -0.1700
Data Index: 743247 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.2599. Min Act: -0.1700
Data Index: 7688074 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.3224. Min Act: -0.1700
Data Index: 8541287 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.2286. Min Act: -0.1700
Data Index: 8065094 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.2599. Min Act: -0.1700
Data Index: 5351150 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7599. Min Range: -6.7599
Max Act: 6.2599. Min Act: -0.1700
Data Index: 228286 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19