Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0991. Min Range: -4.0991
Max Act: 4.0991. Min Act: -0.1700
Data Index: 884350 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0991. Min Range: -4.0991
Max Act: 4.0991. Min Act: -0.1700
Data Index: 1756517 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0991. Min Range: -4.0991
Max Act: 4.0679. Min Act: -0.1700
Data Index: 214416 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.9585. Min Act: -0.1700
Data Index: 667335 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.8959. Min Act: -0.1700
Data Index: 7006682 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.8803. Min Act: -0.1700
Data Index: 5419318 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.8490. Min Act: -0.1700
Data Index: 6531737 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.8334. Min Act: -0.1700
Data Index: 3447685 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.8334. Min Act: -0.1700
Data Index: 3140600 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.8177. Min Act: -0.1700
Data Index: 4777250 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.8021. Min Act: -0.1700
Data Index: 27623 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.7865. Min Act: -0.1700
Data Index: 4247375 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.8021. Min Act: -0.1700
Data Index: 1445017 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.7865. Min Act: -0.1700
Data Index: 3621879 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.7708. Min Act: -0.1700
Data Index: 7545236 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.7552. Min Act: -0.1700
Data Index: 563518 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.7708. Min Act: -0.1700
Data Index: 3355701 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.7552. Min Act: -0.1700
Data Index: 4355015 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.7708. Min Act: -0.1700
Data Index: 1552546 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0991. Min Range: -4.0991
Max Act: 3.7552. Min Act: -0.1700
Data Index: 4001090 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19