Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2510. Min Range: -7.2510
Max Act: 7.2510. Min Act: -0.1700
Data Index: 4247052 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2510. Min Range: -7.2510
Max Act: 7.2198. Min Act: -0.1700
Data Index: 1371319 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2510. Min Range: -7.2510
Max Act: 7.2510. Min Act: -0.1700
Data Index: 1092295 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2510. Min Range: -7.2510
Max Act: 7.0948. Min Act: -0.1700
Data Index: 1673004 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2510. Min Range: -7.2510
Max Act: 7.0948. Min Act: -0.1700
Data Index: 8110592 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2510. Min Range: -7.2510
Max Act: 7.0635. Min Act: -0.1700
Data Index: 8110597 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2510. Min Range: -7.2510
Max Act: 7.0323. Min Act: -0.1700
Data Index: 4476257 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2510. Min Range: -7.2510
Max Act: 7.0323. Min Act: -0.1700
Data Index: 3884662 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2510. Min Range: -7.2510
Max Act: 7.0010. Min Act: -0.1700
Data Index: 1524104 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.9698. Min Act: -0.1700
Data Index: 1075556 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.9385. Min Act: -0.1700
Data Index: 3432057 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.8760. Min Act: -0.1700
Data Index: 6784376 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.8448. Min Act: -0.1700
Data Index: 6985159 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.8135. Min Act: -0.1700
Data Index: 4064087 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.8448. Min Act: -0.1700
Data Index: 668153 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.8448. Min Act: -0.1700
Data Index: 13481 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.8135. Min Act: -0.1700
Data Index: 5731083 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.7823. Min Act: -0.1700
Data Index: 4064082 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.7510. Min Act: -0.1700
Data Index: 3711757 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2510. Min Range: -7.2510
Max Act: 6.7823. Min Act: -0.1700
Data Index: 5609425 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19