Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5943. Min Range: -9.5943
Max Act: 9.5318. Min Act: -0.1700
Data Index: 7642378 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5943. Min Range: -9.5943
Max Act: 9.5943. Min Act: -0.1700
Data Index: 6464356 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5943. Min Range: -9.5943
Max Act: 9.4693. Min Act: -0.1700
Data Index: 882212 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5943. Min Range: -9.5943
Max Act: 9.2818. Min Act: -0.1700
Data Index: 4281246 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5943. Min Range: -9.5943
Max Act: 9.1568. Min Act: -0.1700
Data Index: 854647 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5943. Min Range: -9.5943
Max Act: 9.1568. Min Act: -0.1700
Data Index: 1654879 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5943. Min Range: -9.5943
Max Act: 9.0943. Min Act: -0.1700
Data Index: 1654880 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5943. Min Range: -9.5943
Max Act: 9.0318. Min Act: -0.1700
Data Index: 2625916 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5943. Min Range: -9.5943
Max Act: 9.0318. Min Act: -0.1700
Data Index: 3820479 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5943. Min Range: -9.5943
Max Act: 9.0318. Min Act: -0.1700
Data Index: 6519887 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5943. Min Range: -9.5943
Max Act: 8.9068. Min Act: -0.1700
Data Index: 5717036 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5943. Min Range: -9.5943
Max Act: 8.9068. Min Act: -0.1700
Data Index: 283167 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5943. Min Range: -9.5943
Max Act: 8.9693. Min Act: -0.1700
Data Index: 3570346 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5943. Min Range: -9.5943
Max Act: 8.7818. Min Act: -0.1700
Data Index: 1112974 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5943. Min Range: -9.5943
Max Act: 8.8443. Min Act: -0.1700
Data Index: 1127346 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5943. Min Range: -9.5943
Max Act: 8.8443. Min Act: -0.1700
Data Index: 4398471 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5943. Min Range: -9.5943
Max Act: 8.8443. Min Act: -0.1700
Data Index: 4237062 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5943. Min Range: -9.5943
Max Act: 8.7193. Min Act: -0.1700
Data Index: 5706768 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5943. Min Range: -9.5943
Max Act: 8.7193. Min Act: -0.1700
Data Index: 1776046 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5943. Min Range: -9.5943
Max Act: 8.7193. Min Act: -0.1700
Data Index: 228058 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19