Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5727. Min Act: -0.1700
Data Index: 4570532 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5727. Min Act: -0.1700
Data Index: 2951254 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.5102. Min Act: -0.1700
Data Index: 8332624 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.3539. Min Act: -0.1700
Data Index: 3297672 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.3227. Min Act: -0.1700
Data Index: 1173342 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.3227. Min Act: -0.1700
Data Index: 3561211 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.3227. Min Act: -0.1700
Data Index: 7367684 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2914. Min Act: -0.1700
Data Index: 2854785 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2914. Min Act: -0.1700
Data Index: 1888450 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2914. Min Act: -0.1700
Data Index: 1249592 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2602. Min Act: -0.1700
Data Index: 7212494 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2602. Min Act: -0.1700
Data Index: 813146 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2602. Min Act: -0.1700
Data Index: 7089661 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2602. Min Act: -0.1700
Data Index: 1798342 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2602. Min Act: -0.1700
Data Index: 6605300 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2602. Min Act: -0.1700
Data Index: 8414623 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2602. Min Act: -0.1700
Data Index: 2351688 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.1977. Min Act: -0.1700
Data Index: 3318164 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2289. Min Act: -0.1700
Data Index: 6431122 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5727. Min Range: -5.5727
Max Act: 5.2289. Min Act: -0.1700
Data Index: 3960610 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19