Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 400 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.6933. Min Act: -0.1700
Data Index: 8070624 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.2558. Min Act: -0.1700
Data Index: 6135807 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.1933. Min Act: -0.1700
Data Index: 8338887 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.1621. Min Act: -0.1700
Data Index: 6135809 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.1308. Min Act: -0.1700
Data Index: 3438969 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.0996. Min Act: -0.1700
Data Index: 2242668 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.0683. Min Act: -0.1700
Data Index: 5490079 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.0683. Min Act: -0.1700
Data Index: 3438968 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.0683. Min Act: -0.1700
Data Index: 2242662 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.0371. Min Act: -0.1700
Data Index: 4733983 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.0371. Min Act: -0.1700
Data Index: 5490075 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.0058. Min Act: -0.1700
Data Index: 2242671 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.0058. Min Act: -0.1700
Data Index: 8826557 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.0058. Min Act: -0.1700
Data Index: 7859513 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6933. Min Range: -5.6933
Max Act: 5.0058. Min Act: -0.1700
Data Index: 584025 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6933. Min Range: -5.6933
Max Act: 4.9746. Min Act: -0.1700
Data Index: 3559988 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6933. Min Range: -5.6933
Max Act: 4.9746. Min Act: -0.1700
Data Index: 2242667 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6933. Min Range: -5.6933
Max Act: 4.9746. Min Act: -0.1700
Data Index: 6052451 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6933. Min Range: -5.6933
Max Act: 4.9746. Min Act: -0.1700
Data Index: 7859512 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6933. Min Range: -5.6933
Max Act: 4.9433. Min Act: -0.1700
Data Index: 1107002 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19