Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5350 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2389. Min Range: -9.2389
Max Act: 9.2389. Min Act: -0.1700
Data Index: 4671472 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.7389. Min Act: -0.1700
Data Index: 3776843 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.6139. Min Act: -0.1700
Data Index: 484233 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.6139. Min Act: -0.1700
Data Index: 4923266 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.4889. Min Act: -0.1700
Data Index: 4256207 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.4264. Min Act: -0.1700
Data Index: 1335838 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.4264. Min Act: -0.1700
Data Index: 3779336 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.3639. Min Act: -0.1700
Data Index: 4771729 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.3639. Min Act: -0.1700
Data Index: 4505320 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.3639. Min Act: -0.1700
Data Index: 2392261 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.3014. Min Act: -0.1700
Data Index: 7666790 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.3014. Min Act: -0.1700
Data Index: 8757139 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.3014. Min Act: -0.1700
Data Index: 5897697 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.2389. Min Act: -0.1700
Data Index: 2270477 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.3014. Min Act: -0.1700
Data Index: 2306900 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.2389. Min Act: -0.1700
Data Index: 6665600 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.2389. Min Act: -0.1700
Data Index: 8436128 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.2389. Min Act: -0.1700
Data Index: 7223343 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.1764. Min Act: -0.1700
Data Index: 7855632 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2389. Min Range: -9.2389
Max Act: 8.1764. Min Act: -0.1700
Data Index: 1981069 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19