Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2953. Min Act: -0.1700
Data Index: 2310121 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2824. Min Act: -0.1700
Data Index: 477391 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2760. Min Act: -0.1656
Data Index: 5610418 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2447. Min Act: -0.1695
Data Index: 7748188 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2509. Min Act: -0.1700
Data Index: 3240583 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2447. Min Act: -0.1656
Data Index: 146165 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2447. Min Act: -0.1698
Data Index: 7415754 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2447. Min Act: -0.1656
Data Index: 8263566 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2447. Min Act: -0.1674
Data Index: 1199277 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2447. Min Act: -0.1694
Data Index: 1140894 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2447. Min Act: -0.1687
Data Index: 861688 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2447. Min Act: -0.1656
Data Index: 637607 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2447. Min Act: -0.1697
Data Index: 5699020 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2447. Min Act: -0.1700
Data Index: 8051139 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2325. Min Act: -0.1656
Data Index: 1592592 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2264. Min Act: -0.1664
Data Index: 4473480 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2264. Min Act: -0.1698
Data Index: 1717541 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2264. Min Act: -0.1695
Data Index: 1355582 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2145. Min Act: -0.1700
Data Index: 3197767 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2953. Min Range: -0.2953
Max Act: 0.2086. Min Act: -0.1699
Data Index: 5219495 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19