Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6089 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2495. Min Range: -7.2495
Max Act: 7.2495. Min Act: -0.1700
Data Index: 5030883 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2495. Min Range: -7.2495
Max Act: 7.2183. Min Act: -0.1700
Data Index: 8595914 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.9683. Min Act: -0.1700
Data Index: 6075349 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.9683. Min Act: -0.1700
Data Index: 6928330 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.9995. Min Act: -0.1700
Data Index: 1053698 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.9058. Min Act: -0.1700
Data Index: 4843809 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.8433. Min Act: -0.1700
Data Index: 1514657 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.8120. Min Act: -0.1700
Data Index: 3733197 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.7808. Min Act: -0.1700
Data Index: 7805921 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.7808. Min Act: -0.1700
Data Index: 3189183 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.7495. Min Act: -0.1700
Data Index: 3415949 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.6870. Min Act: -0.1700
Data Index: 8438855 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.6870. Min Act: -0.1700
Data Index: 389714 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.6558. Min Act: -0.1700
Data Index: 5056570 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.6558. Min Act: -0.1700
Data Index: 7033318 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.6558. Min Act: -0.1700
Data Index: 5814444 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.6245. Min Act: -0.1700
Data Index: 1467893 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.5933. Min Act: -0.1700
Data Index: 8067352 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.5933. Min Act: -0.1700
Data Index: 4190633 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2495. Min Range: -7.2495
Max Act: 6.5933. Min Act: -0.1700
Data Index: 8030528 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19