Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.9028. Min Act: -0.1700
Data Index: 4645842 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.7756. Min Act: -0.1700
Data Index: 5574948 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.7437. Min Act: -0.1700
Data Index: 195598 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.7277. Min Act: -0.1700
Data Index: 998821 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6958. Min Act: -0.1700
Data Index: 3290761 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6797. Min Act: -0.1697
Data Index: 702230 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6637. Min Act: -0.1700
Data Index: 817241 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6637. Min Act: -0.1700
Data Index: 459602 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6797. Min Act: -0.1700
Data Index: 6857081 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6477. Min Act: -0.1693
Data Index: 3204035 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6477. Min Act: -0.1700
Data Index: 7828537 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6316. Min Act: -0.1689
Data Index: 7000334 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6155. Min Act: -0.1698
Data Index: 2788362 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6155. Min Act: -0.1700
Data Index: 6269610 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6155. Min Act: -0.1700
Data Index: 3562773 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.6155. Min Act: -0.1700
Data Index: 195599 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.5995. Min Act: -0.1700
Data Index: 4361149 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.5995. Min Act: -0.1696
Data Index: 3206932 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.5834. Min Act: -0.1693
Data Index: 4093937 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9028. Min Range: -2.9028
Max Act: 2.5995. Min Act: -0.1700
Data Index: 1390255 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19