Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1582 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2186. Min Range: -7.2186
Max Act: 7.2186. Min Act: -0.1700
Data Index: 921644 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2186. Min Range: -7.2186
Max Act: 7.1249. Min Act: -0.1700
Data Index: 7022348 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2186. Min Range: -7.2186
Max Act: 7.1249. Min Act: -0.1700
Data Index: 921646 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2186. Min Range: -7.2186
Max Act: 7.0311. Min Act: -0.1700
Data Index: 921645 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.9061. Min Act: -0.1700
Data Index: 472863 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.8749. Min Act: -0.1700
Data Index: 472883 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.8436. Min Act: -0.1700
Data Index: 6718385 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.8124. Min Act: -0.1700
Data Index: 8023896 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.6249. Min Act: -0.1700
Data Index: 472867 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.6249. Min Act: -0.1700
Data Index: 7158577 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.6249. Min Act: -0.1700
Data Index: 7528800 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.5311. Min Act: -0.1700
Data Index: 472889 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.5936. Min Act: -0.1700
Data Index: 169080 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.5936. Min Act: -0.1700
Data Index: 472864 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.5624. Min Act: -0.1700
Data Index: 472884 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.5311. Min Act: -0.1700
Data Index: 6315516 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.4686. Min Act: -0.1700
Data Index: 8541924 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.4999. Min Act: -0.1700
Data Index: 3191808 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.4999. Min Act: -0.1700
Data Index: 694896 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2186. Min Range: -7.2186
Max Act: 6.4999. Min Act: -0.1700
Data Index: 2273281 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19