Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.9738. Min Act: -0.1700
Data Index: 5335630 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.9113. Min Act: -0.1700
Data Index: 6513472 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.9113. Min Act: -0.1700
Data Index: 8060964 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.7863. Min Act: -0.1700
Data Index: 7505563 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.6301. Min Act: -0.1700
Data Index: 6197535 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.5988. Min Act: -0.1700
Data Index: 7163637 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.5676. Min Act: -0.1700
Data Index: 6543750 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.5676. Min Act: -0.1700
Data Index: 4606984 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.5676. Min Act: -0.1700
Data Index: 351007 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.5051. Min Act: -0.1700
Data Index: 953535 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.5051. Min Act: -0.1700
Data Index: 5854145 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.4113. Min Act: -0.1700
Data Index: 8060957 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.4738. Min Act: -0.1700
Data Index: 5889547 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.4113. Min Act: -0.1700
Data Index: 7714418 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.4426. Min Act: -0.1700
Data Index: 1523227 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.3488. Min Act: -0.1700
Data Index: 825838 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.3488. Min Act: -0.1700
Data Index: 7841831 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.3801. Min Act: -0.1700
Data Index: 7390573 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.2863. Min Act: -0.1700
Data Index: 5561294 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9738. Min Range: -7.9738
Max Act: 7.2863. Min Act: -0.1700
Data Index: 7652790 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19