Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1671 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.9328. Min Act: -0.1700
Data Index: 3557877 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.8702. Min Act: -0.1700
Data Index: 262063 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.8077. Min Act: -0.1700
Data Index: 3479112 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.8077. Min Act: -0.1700
Data Index: 4583838 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.7764. Min Act: -0.1700
Data Index: 2639253 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.7764. Min Act: -0.1700
Data Index: 6443591 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.7451. Min Act: -0.1700
Data Index: 8352913 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.7451. Min Act: -0.1700
Data Index: 5574154 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.7139. Min Act: -0.1700
Data Index: 4266626 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.7451. Min Act: -0.1700
Data Index: 8284249 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.6826. Min Act: -0.1700
Data Index: 2314213 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.6826. Min Act: -0.1700
Data Index: 1257928 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.6826. Min Act: -0.1700
Data Index: 649050 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.6826. Min Act: -0.1700
Data Index: 6983142 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.6826. Min Act: -0.1700
Data Index: 7740364 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.6669. Min Act: -0.1700
Data Index: 4840977 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.6513. Min Act: -0.1700
Data Index: 3100322 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.6669. Min Act: -0.1700
Data Index: 5751473 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.6669. Min Act: -0.1700
Data Index: 91630 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9328. Min Range: -3.9328
Max Act: 3.6669. Min Act: -0.1700
Data Index: 3845 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19