Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.9278. Min Act: -0.1700
Data Index: 8703183 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.8028. Min Act: -0.1700
Data Index: 6023342 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.7403. Min Act: -0.1700
Data Index: 4801337 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.7403. Min Act: -0.1700
Data Index: 1509935 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.7090. Min Act: -0.1700
Data Index: 5597365 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.7090. Min Act: -0.1700
Data Index: 1796367 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.6778. Min Act: -0.1700
Data Index: 1726614 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.6465. Min Act: -0.1700
Data Index: 8722942 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.6153. Min Act: -0.1700
Data Index: 3342514 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.6153. Min Act: -0.1700
Data Index: 480492 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.6153. Min Act: -0.1700
Data Index: 5156610 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.5840. Min Act: -0.1700
Data Index: 5276448 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.5840. Min Act: -0.1700
Data Index: 2090664 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.5840. Min Act: -0.1700
Data Index: 8791329 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.5528. Min Act: -0.1700
Data Index: 4696638 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.5528. Min Act: -0.1700
Data Index: 5821511 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.5528. Min Act: -0.1700
Data Index: 7677242 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.5528. Min Act: -0.1700
Data Index: 4971856 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.5215. Min Act: -0.1700
Data Index: 1092342 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9278. Min Range: -6.9278
Max Act: 6.5528. Min Act: -0.1700
Data Index: 7728442 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19