Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4527 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.9955. Min Act: -0.1700
Data Index: 8801816 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.8392. Min Act: -0.1700
Data Index: 1306908 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.6830. Min Act: -0.1700
Data Index: 7979290 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.6205. Min Act: -0.1700
Data Index: 8215020 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.5892. Min Act: -0.1700
Data Index: 116788 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.5580. Min Act: -0.1700
Data Index: 2542667 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.5580. Min Act: -0.1700
Data Index: 32955 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.4955. Min Act: -0.1700
Data Index: 6887085 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.4955. Min Act: -0.1700
Data Index: 3472614 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.4330. Min Act: -0.1700
Data Index: 325730 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.4642. Min Act: -0.1700
Data Index: 7451970 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.4642. Min Act: -0.1700
Data Index: 5607010 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.4330. Min Act: -0.1700
Data Index: 1218442 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.4330. Min Act: -0.1700
Data Index: 6046051 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.3705. Min Act: -0.1700
Data Index: 722148 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.3392. Min Act: -0.1700
Data Index: 3100208 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.3392. Min Act: -0.1700
Data Index: 7463814 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.3080. Min Act: -0.1700
Data Index: 7297963 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.3080. Min Act: -0.1700
Data Index: 8635015 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9955. Min Range: -5.9955
Max Act: 5.3080. Min Act: -0.1700
Data Index: 2465798 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19