Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 221 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.8569. Min Act: -0.1700
Data Index: 4755151 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.7944. Min Act: -0.1700
Data Index: 4924543 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.7944. Min Act: -0.1700
Data Index: 4880324 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.5444. Min Act: -0.1700
Data Index: 3576458 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.6069. Min Act: -0.1700
Data Index: 8505675 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.3569. Min Act: -0.1700
Data Index: 6050800 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.2944. Min Act: -0.1700
Data Index: 2771013 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.2319. Min Act: -0.1700
Data Index: 1875843 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.2944. Min Act: -0.1700
Data Index: 1638974 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.1694. Min Act: -0.1700
Data Index: 7589929 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.1694. Min Act: -0.1700
Data Index: 1229208 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.1694. Min Act: -0.1700
Data Index: 1822327 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.1694. Min Act: -0.1700
Data Index: 6346879 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.1694. Min Act: -0.1700
Data Index: 4875729 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.1694. Min Act: -0.1700
Data Index: 3475257 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.1069. Min Act: -0.1700
Data Index: 3576552 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8569. Min Range: -8.8569
Max Act: 8.0444. Min Act: -0.1700
Data Index: 7025302 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8569. Min Range: -8.8569
Max Act: 7.9819. Min Act: -0.1700
Data Index: 1554286 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8569. Min Range: -8.8569
Max Act: 7.9819. Min Act: -0.1700
Data Index: 7414321 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8569. Min Range: -8.8569
Max Act: 7.9819. Min Act: -0.1700
Data Index: 1020507 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19