Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2488. Min Range: -7.2488
Max Act: 7.2488. Min Act: -0.1700
Data Index: 6452446 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2488. Min Range: -7.2488
Max Act: 7.1863. Min Act: -0.1700
Data Index: 1263492 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2488. Min Range: -7.2488
Max Act: 7.1238. Min Act: -0.1700
Data Index: 6991685 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2488. Min Range: -7.2488
Max Act: 7.0300. Min Act: -0.1700
Data Index: 3270660 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.9675. Min Act: -0.1700
Data Index: 3270658 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.8113. Min Act: -0.1700
Data Index: 2657507 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7800. Min Act: -0.1700
Data Index: 2110101 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.8425. Min Act: -0.1700
Data Index: 2632633 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7800. Min Act: -0.1700
Data Index: 4265820 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7800. Min Act: -0.1700
Data Index: 1591392 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7175. Min Act: -0.1700
Data Index: 2934857 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7800. Min Act: -0.1700
Data Index: 5756846 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7175. Min Act: -0.1700
Data Index: 8776271 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7175. Min Act: -0.1700
Data Index: 3314316 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7488. Min Act: -0.1700
Data Index: 3782346 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7175. Min Act: -0.1700
Data Index: 20597 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7488. Min Act: -0.1700
Data Index: 2172196 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.7175. Min Act: -0.1700
Data Index: 2989336 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.6863. Min Act: -0.1700
Data Index: 457420 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2488. Min Range: -7.2488
Max Act: 6.6863. Min Act: -0.1700
Data Index: 6348306 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19