Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.7556. Min Act: -0.1700
Data Index: 6825231 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.6306. Min Act: -0.1700
Data Index: 2037768 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.5993. Min Act: -0.1700
Data Index: 8256915 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.5056. Min Act: -0.1700
Data Index: 1297011 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.5056. Min Act: -0.1700
Data Index: 5660784 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.5368. Min Act: -0.1700
Data Index: 5960357 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.5056. Min Act: -0.1700
Data Index: 5825599 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.5056. Min Act: -0.1700
Data Index: 1898389 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.4431. Min Act: -0.1700
Data Index: 297153 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.4431. Min Act: -0.1700
Data Index: 2670040 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.4118. Min Act: -0.1700
Data Index: 4191804 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.4118. Min Act: -0.1700
Data Index: 7945690 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.3493. Min Act: -0.1697
Data Index: 8333017 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.3806. Min Act: -0.1700
Data Index: 3733806 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.3493. Min Act: -0.1700
Data Index: 6175134 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.3493. Min Act: -0.1700
Data Index: 7204180 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.3493. Min Act: -0.1700
Data Index: 3027230 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.3806. Min Act: -0.1700
Data Index: 1604710 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.3493. Min Act: -0.1700
Data Index: 7005565 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7556. Min Range: -6.7556
Max Act: 6.3493. Min Act: -0.1700
Data Index: 88207 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19