Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1976. Min Range: -4.1976
Max Act: 4.1976. Min Act: -0.1700
Data Index: 133142 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1976. Min Range: -4.1976
Max Act: 4.1976. Min Act: -0.1700
Data Index: 8239337 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1976. Min Range: -4.1976
Max Act: 4.1664. Min Act: -0.1700
Data Index: 232421 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1976. Min Range: -4.1976
Max Act: 4.1351. Min Act: -0.1700
Data Index: 6238398 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1976. Min Range: -4.1976
Max Act: 4.1351. Min Act: -0.1700
Data Index: 3032554 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1976. Min Range: -4.1976
Max Act: 4.1038. Min Act: -0.1700
Data Index: 2015874 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1976. Min Range: -4.1976
Max Act: 4.0413. Min Act: -0.1700
Data Index: 4762171 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1976. Min Range: -4.1976
Max Act: 4.0413. Min Act: -0.1700
Data Index: 3872886 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1976. Min Range: -4.1976
Max Act: 4.0101. Min Act: -0.1700
Data Index: 7500580 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.9788. Min Act: -0.1700
Data Index: 1892921 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.9475. Min Act: -0.1700
Data Index: 313060 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.9163. Min Act: -0.1700
Data Index: 394351 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.8850. Min Act: -0.1700
Data Index: 5591734 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.9163. Min Act: -0.1700
Data Index: 993649 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.9163. Min Act: -0.1700
Data Index: 8127477 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.9163. Min Act: -0.1700
Data Index: 2810464 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.9163. Min Act: -0.1700
Data Index: 4658948 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.9163. Min Act: -0.1700
Data Index: 895367 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.8538. Min Act: -0.1700
Data Index: 6651049 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1976. Min Range: -4.1976
Max Act: 3.8538. Min Act: -0.1700
Data Index: 5146391 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19