Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1618 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2853. Min Range: -5.2853
Max Act: 5.2853. Min Act: -0.1700
Data Index: 703538 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2853. Min Range: -5.2853
Max Act: 5.0040. Min Act: -0.1700
Data Index: 4389746 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.9728. Min Act: -0.1700
Data Index: 1355343 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.9415. Min Act: -0.1700
Data Index: 3475867 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.9728. Min Act: -0.1700
Data Index: 1379790 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.9415. Min Act: -0.1700
Data Index: 3243561 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.9103. Min Act: -0.1700
Data Index: 4526069 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.9103. Min Act: -0.1700
Data Index: 8776329 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.9103. Min Act: -0.1700
Data Index: 339944 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.8790. Min Act: -0.1700
Data Index: 4217798 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.8790. Min Act: -0.1700
Data Index: 387486 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.8790. Min Act: -0.1700
Data Index: 4237478 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.8478. Min Act: -0.1700
Data Index: 7594895 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.8165. Min Act: -0.1700
Data Index: 1520213 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.8165. Min Act: -0.1700
Data Index: 6354712 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.8165. Min Act: -0.1700
Data Index: 1361775 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.8165. Min Act: -0.1700
Data Index: 1522437 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.7853. Min Act: -0.1700
Data Index: 7422854 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.7853. Min Act: -0.1700
Data Index: 6616169 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2853. Min Range: -5.2853
Max Act: 4.8165. Min Act: -0.1700
Data Index: 4796505 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19