Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3213 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0010. Min Range: -6.0010
Max Act: 6.0010. Min Act: -0.1700
Data Index: 6169222 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.9073. Min Act: -0.1700
Data Index: 6595493 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.8760. Min Act: -0.1700
Data Index: 6219685 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.8760. Min Act: -0.1700
Data Index: 8450296 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.8760. Min Act: -0.1700
Data Index: 8504374 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.8135. Min Act: -0.1700
Data Index: 3004059 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.8448. Min Act: -0.1700
Data Index: 1259143 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.8448. Min Act: -0.1700
Data Index: 2054660 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7823. Min Act: -0.1700
Data Index: 3705703 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7823. Min Act: -0.1700
Data Index: 5800957 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7823. Min Act: -0.1700
Data Index: 5293061 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7198. Min Act: -0.1700
Data Index: 3736931 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7510. Min Act: -0.1700
Data Index: 7621834 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7198. Min Act: -0.1700
Data Index: 1111721 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7198. Min Act: -0.1700
Data Index: 6181319 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7198. Min Act: -0.1700
Data Index: 5960684 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7510. Min Act: -0.1700
Data Index: 1031174 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7198. Min Act: -0.1700
Data Index: 4104062 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7510. Min Act: -0.1700
Data Index: 5077917 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0010. Min Range: -6.0010
Max Act: 5.7198. Min Act: -0.1700
Data Index: 7223059 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19