Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1431. Min Range: -9.1431
Max Act: 9.1431. Min Act: -0.1700
Data Index: 7729436 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1431. Min Range: -9.1431
Max Act: 9.0806. Min Act: -0.1700
Data Index: 117798 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.9556. Min Act: -0.1700
Data Index: 2190531 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.8306. Min Act: -0.1700
Data Index: 8470974 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.7056. Min Act: -0.1700
Data Index: 3425075 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.7681. Min Act: -0.1700
Data Index: 5440708 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.6431. Min Act: -0.1700
Data Index: 7729437 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.5806. Min Act: -0.1700
Data Index: 2668185 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.6431. Min Act: -0.1700
Data Index: 2431130 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.5181. Min Act: -0.1700
Data Index: 7981230 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.5181. Min Act: -0.1700
Data Index: 582682 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.5181. Min Act: -0.1700
Data Index: 622709 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.4556. Min Act: -0.1700
Data Index: 4392078 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.4556. Min Act: -0.1700
Data Index: 7486278 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.4556. Min Act: -0.1700
Data Index: 6094761 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.4556. Min Act: -0.1700
Data Index: 5954548 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.3931. Min Act: -0.1700
Data Index: 5238219 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.3931. Min Act: -0.1700
Data Index: 560635 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.3931. Min Act: -0.1700
Data Index: 7835017 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1431. Min Range: -9.1431
Max Act: 8.3931. Min Act: -0.1700
Data Index: 1118491 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19