Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1995 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1237. Min Range: -7.1237
Max Act: 7.1237. Min Act: -0.1700
Data Index: 6814808 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1237. Min Range: -7.1237
Max Act: 7.0612. Min Act: -0.1700
Data Index: 8447207 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1237. Min Range: -7.1237
Max Act: 7.0612. Min Act: -0.1700
Data Index: 7361258 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1237. Min Range: -7.1237
Max Act: 7.0299. Min Act: -0.1700
Data Index: 2978086 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1237. Min Range: -7.1237
Max Act: 7.0299. Min Act: -0.1700
Data Index: 5207432 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.9987. Min Act: -0.1700
Data Index: 6071529 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.9674. Min Act: -0.1700
Data Index: 6437195 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.9362. Min Act: -0.1700
Data Index: 7728141 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.9362. Min Act: -0.1700
Data Index: 4431919 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.9362. Min Act: -0.1700
Data Index: 1265703 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.8112. Min Act: -0.1700
Data Index: 246250 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.7174. Min Act: -0.1700
Data Index: 8455660 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.6549. Min Act: -0.1700
Data Index: 4496479 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.5612. Min Act: -0.1700
Data Index: 126145 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.5924. Min Act: -0.1700
Data Index: 2377384 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.5299. Min Act: -0.1700
Data Index: 1611865 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.5299. Min Act: -0.1700
Data Index: 8752634 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.5299. Min Act: -0.1700
Data Index: 6103904 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.5299. Min Act: -0.1700
Data Index: 282699 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1237. Min Range: -7.1237
Max Act: 6.4987. Min Act: -0.1700
Data Index: 2418983 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19