Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4447. Min Range: -5.4447
Max Act: 5.4447. Min Act: -0.1700
Data Index: 2191568 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4447. Min Range: -5.4447
Max Act: 5.2884. Min Act: -0.1700
Data Index: 4288856 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4447. Min Range: -5.4447
Max Act: 5.1947. Min Act: -0.1700
Data Index: 396584 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4447. Min Range: -5.4447
Max Act: 5.1009. Min Act: -0.1700
Data Index: 541571 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4447. Min Range: -5.4447
Max Act: 5.0697. Min Act: -0.1700
Data Index: 1757118 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4447. Min Range: -5.4447
Max Act: 5.0384. Min Act: -0.1700
Data Index: 7228825 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4447. Min Range: -5.4447
Max Act: 5.0384. Min Act: -0.1700
Data Index: 6746379 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.9759. Min Act: -0.1700
Data Index: 5006017 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4447. Min Range: -5.4447
Max Act: 5.0072. Min Act: -0.1700
Data Index: 4904832 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.9759. Min Act: -0.1700
Data Index: 1202640 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.9447. Min Act: -0.1700
Data Index: 5340204 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.9447. Min Act: -0.1700
Data Index: 5783626 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.9134. Min Act: -0.1700
Data Index: 635215 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.9134. Min Act: -0.1700
Data Index: 1201278 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.9134. Min Act: -0.1700
Data Index: 2489226 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.9134. Min Act: -0.1700
Data Index: 4845875 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.8822. Min Act: -0.1700
Data Index: 647161 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.8509. Min Act: -0.1700
Data Index: 6428018 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.8822. Min Act: -0.1700
Data Index: 3507891 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4447. Min Range: -5.4447
Max Act: 4.8509. Min Act: -0.1700
Data Index: 3524223 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19