Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.7334. Min Act: -0.1675
Data Index: 3371858 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.6843. Min Act: -0.1695
Data Index: 7107737 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.6681. Min Act: -0.1697
Data Index: 5608160 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.6360. Min Act: -0.1698
Data Index: 6276704 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.6280. Min Act: -0.1688
Data Index: 7651179 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.6201. Min Act: -0.1700
Data Index: 5453548 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.6043. Min Act: -0.1693
Data Index: 4920401 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.6043. Min Act: -0.1698
Data Index: 5125217 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5885. Min Act: -0.1699
Data Index: 1886894 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5885. Min Act: -0.1700
Data Index: 1905478 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5729. Min Act: -0.1700
Data Index: 3396317 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5729. Min Act: -0.1673
Data Index: 1632344 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5729. Min Act: -0.1700
Data Index: 2306320 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5729. Min Act: -0.1674
Data Index: 2273813 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5652. Min Act: -0.1679
Data Index: 538339 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5652. Min Act: -0.1699
Data Index: 1609457 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5652. Min Act: -0.1700
Data Index: 1947714 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5652. Min Act: -0.1700
Data Index: 2020893 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5652. Min Act: -0.1698
Data Index: 3132582 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7334. Min Range: -0.7334
Max Act: 0.5497. Min Act: -0.1698
Data Index: 116610 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19