Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5560 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.3309. Min Act: -0.1700
Data Index: 7479189 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.2371. Min Act: -0.1700
Data Index: 2395035 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.2371. Min Act: -0.1700
Data Index: 1455180 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.1434. Min Act: -0.1700
Data Index: 7564722 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.1434. Min Act: -0.1700
Data Index: 5947172 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.1121. Min Act: -0.1700
Data Index: 2449472 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.1434. Min Act: -0.1700
Data Index: 3203876 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0809. Min Act: -0.1700
Data Index: 3104723 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0183. Min Act: -0.1700
Data Index: 151612 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0496. Min Act: -0.1700
Data Index: 5365459 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0183. Min Act: -0.1700
Data Index: 3300014 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0183. Min Act: -0.1700
Data Index: 6386498 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3309. Min Range: -4.3309
Max Act: 3.9871. Min Act: -0.1700
Data Index: 1171283 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0183. Min Act: -0.1700
Data Index: 4688264 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0183. Min Act: -0.1700
Data Index: 7960163 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0496. Min Act: -0.1700
Data Index: 1200109 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0183. Min Act: -0.1700
Data Index: 2620476 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0183. Min Act: -0.1700
Data Index: 6642158 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3309. Min Range: -4.3309
Max Act: 4.0183. Min Act: -0.1700
Data Index: 5324994 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3309. Min Range: -4.3309
Max Act: 3.9871. Min Act: -0.1700
Data Index: 7960164 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19