Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2758 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2187. Min Range: -6.2187
Max Act: 6.2187. Min Act: -0.1700
Data Index: 5005918 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2187. Min Range: -6.2187
Max Act: 6.0625. Min Act: -0.1700
Data Index: 7488300 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.9062. Min Act: -0.1700
Data Index: 3172553 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.8750. Min Act: -0.1700
Data Index: 3023133 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.9062. Min Act: -0.1700
Data Index: 5436648 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.8437. Min Act: -0.1700
Data Index: 5580684 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.8437. Min Act: -0.1700
Data Index: 3235184 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.8437. Min Act: -0.1700
Data Index: 2661472 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.7500. Min Act: -0.1700
Data Index: 771479 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.7812. Min Act: -0.1700
Data Index: 4624554 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.7500. Min Act: -0.1700
Data Index: 1689300 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.7500. Min Act: -0.1700
Data Index: 5037419 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.7500. Min Act: -0.1700
Data Index: 7359045 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.7187. Min Act: -0.1700
Data Index: 422766 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.7187. Min Act: -0.1700
Data Index: 6198020 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.6562. Min Act: -0.1700
Data Index: 6523344 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.6875. Min Act: -0.1700
Data Index: 6693800 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.6875. Min Act: -0.1700
Data Index: 3580691 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.6875. Min Act: -0.1700
Data Index: 24246 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2187. Min Range: -6.2187
Max Act: 5.6875. Min Act: -0.1700
Data Index: 6492833 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19