Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1606. Min Range: -6.1606
Max Act: 6.1606. Min Act: -0.1700
Data Index: 3866200 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1606. Min Range: -6.1606
Max Act: 6.1293. Min Act: -0.1700
Data Index: 1218708 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.8793. Min Act: -0.1700
Data Index: 541188 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.8793. Min Act: -0.1700
Data Index: 952837 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.8793. Min Act: -0.1700
Data Index: 4285605 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.8168. Min Act: -0.1700
Data Index: 8032478 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.8168. Min Act: -0.1700
Data Index: 2003645 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7856. Min Act: -0.1700
Data Index: 5072677 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7856. Min Act: -0.1700
Data Index: 1164908 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7856. Min Act: -0.1700
Data Index: 1218707 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7856. Min Act: -0.1700
Data Index: 4285606 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7543. Min Act: -0.1700
Data Index: 435007 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7543. Min Act: -0.1700
Data Index: 1170119 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7543. Min Act: -0.1700
Data Index: 6143497 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7231. Min Act: -0.1700
Data Index: 8024198 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7231. Min Act: -0.1700
Data Index: 5708924 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7231. Min Act: -0.1700
Data Index: 4123948 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7231. Min Act: -0.1700
Data Index: 461259 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7231. Min Act: -0.1700
Data Index: 680100 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1606. Min Range: -6.1606
Max Act: 5.7231. Min Act: -0.1700
Data Index: 2042395 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19