Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3653 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2054. Min Range: -5.2054
Max Act: 5.2054. Min Act: -0.1700
Data Index: 3018798 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2054. Min Range: -5.2054
Max Act: 5.1116. Min Act: -0.1700
Data Index: 5598104 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2054. Min Range: -5.2054
Max Act: 5.0804. Min Act: -0.1700
Data Index: 7036851 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2054. Min Range: -5.2054
Max Act: 5.0491. Min Act: -0.1700
Data Index: 7208496 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2054. Min Range: -5.2054
Max Act: 5.0179. Min Act: -0.1700
Data Index: 2551850 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9866. Min Act: -0.1700
Data Index: 1687692 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9866. Min Act: -0.1700
Data Index: 7036850 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9866. Min Act: -0.1700
Data Index: 1431698 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9554. Min Act: -0.1700
Data Index: 752787 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9554. Min Act: -0.1700
Data Index: 752786 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9554. Min Act: -0.1700
Data Index: 4753724 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9554. Min Act: -0.1700
Data Index: 2551859 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9241. Min Act: -0.1700
Data Index: 3018789 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9241. Min Act: -0.1700
Data Index: 5924368 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9241. Min Act: -0.1700
Data Index: 1431696 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9241. Min Act: -0.1700
Data Index: 1431701 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.9241. Min Act: -0.1700
Data Index: 5202684 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.8929. Min Act: -0.1700
Data Index: 7036842 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.8929. Min Act: -0.1700
Data Index: 3100190 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2054. Min Range: -5.2054
Max Act: 4.8929. Min Act: -0.1700
Data Index: 3018791 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19