Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3230 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3496. Min Range: -8.3496
Max Act: 8.3496. Min Act: -0.1700
Data Index: 8062579 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.9121. Min Act: -0.1700
Data Index: 4825710 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.8184. Min Act: -0.1700
Data Index: 3585630 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.7871. Min Act: -0.1700
Data Index: 7811662 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.8184. Min Act: -0.1700
Data Index: 8324815 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.7559. Min Act: -0.1700
Data Index: 7846882 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.7246. Min Act: -0.1700
Data Index: 2116375 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.6309. Min Act: -0.1700
Data Index: 6868505 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.6309. Min Act: -0.1700
Data Index: 4070503 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.6309. Min Act: -0.1700
Data Index: 212270 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.5996. Min Act: -0.1700
Data Index: 805698 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.5996. Min Act: -0.1700
Data Index: 1327732 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.5371. Min Act: -0.1700
Data Index: 3129796 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.5684. Min Act: -0.1700
Data Index: 6328724 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.5059. Min Act: -0.1700
Data Index: 8337884 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.4434. Min Act: -0.1700
Data Index: 3968274 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.3809. Min Act: -0.1700
Data Index: 7981654 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.4121. Min Act: -0.1700
Data Index: 1440065 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.4121. Min Act: -0.1700
Data Index: 8572625 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3496. Min Range: -8.3496
Max Act: 7.4121. Min Act: -0.1700
Data Index: 8098367 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19