Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4622 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.8595. Min Act: -0.1700
Data Index: 2566733 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.8595. Min Act: -0.1700
Data Index: 4923368 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.7970. Min Act: -0.1700
Data Index: 665534 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.7970. Min Act: -0.1700
Data Index: 1697462 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.6720. Min Act: -0.1700
Data Index: 6752990 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.5470. Min Act: -0.1700
Data Index: 2581475 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.5470. Min Act: -0.1700
Data Index: 2290263 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.4845. Min Act: -0.1700
Data Index: 8334087 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.4845. Min Act: -0.1700
Data Index: 227725 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.4532. Min Act: -0.1700
Data Index: 6988523 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.4532. Min Act: -0.1700
Data Index: 2227137 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.4220. Min Act: -0.1700
Data Index: 7922797 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.4532. Min Act: -0.1700
Data Index: 5806775 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.4220. Min Act: -0.1700
Data Index: 1135614 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.4220. Min Act: -0.1700
Data Index: 4527949 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.4220. Min Act: -0.1700
Data Index: 6992414 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.3907. Min Act: -0.1700
Data Index: 6396444 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.4220. Min Act: -0.1700
Data Index: 7719377 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.3282. Min Act: -0.1700
Data Index: 2078305 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8595. Min Range: -7.8595
Max Act: 7.3282. Min Act: -0.1700
Data Index: 70053 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19