Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5270 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.5227. Min Act: -0.1700
Data Index: 2069237 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.4914. Min Act: -0.1700
Data Index: 8044163 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.4914. Min Act: -0.1700
Data Index: 5952317 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.4602. Min Act: -0.1700
Data Index: 2679096 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.3977. Min Act: -0.1700
Data Index: 2439271 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.3664. Min Act: -0.1700
Data Index: 925031 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.3977. Min Act: -0.1700
Data Index: 1723221 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.3352. Min Act: -0.1700
Data Index: 1723206 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.3352. Min Act: -0.1700
Data Index: 7070912 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.3039. Min Act: -0.1700
Data Index: 2559881 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.3039. Min Act: -0.1700
Data Index: 2794148 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.3039. Min Act: -0.1700
Data Index: 6891631 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.2727. Min Act: -0.1700
Data Index: 6886104 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.3039. Min Act: -0.1700
Data Index: 4962829 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.3039. Min Act: -0.1700
Data Index: 7901985 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.2727. Min Act: -0.1700
Data Index: 3704687 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.2727. Min Act: -0.1700
Data Index: 1310262 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.2727. Min Act: -0.1700
Data Index: 1402959 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.2727. Min Act: -0.1700
Data Index: 1583636 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5227. Min Range: -4.5227
Max Act: 4.2727. Min Act: -0.1700
Data Index: 855109 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19