Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4609 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2733. Min Range: -5.2733
Max Act: 5.2733. Min Act: -0.1700
Data Index: 2272422 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2733. Min Range: -5.2733
Max Act: 5.2108. Min Act: -0.1700
Data Index: 1659072 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2733. Min Range: -5.2733
Max Act: 5.0545. Min Act: -0.1700
Data Index: 482045 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2733. Min Range: -5.2733
Max Act: 5.0545. Min Act: -0.1700
Data Index: 6537125 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.8670. Min Act: -0.1700
Data Index: 123873 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.8358. Min Act: -0.1700
Data Index: 1601222 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.8045. Min Act: -0.1700
Data Index: 8209606 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.8045. Min Act: -0.1700
Data Index: 5189360 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.7733. Min Act: -0.1700
Data Index: 1570927 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.7733. Min Act: -0.1700
Data Index: 4872697 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.7420. Min Act: -0.1700
Data Index: 332637 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.7420. Min Act: -0.1700
Data Index: 951544 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 6284557 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 8192472 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 2655758 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.7108. Min Act: -0.1700
Data Index: 5019471 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.6795. Min Act: -0.1700
Data Index: 280100 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.6795. Min Act: -0.1700
Data Index: 5458084 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.6483. Min Act: -0.1700
Data Index: 7968776 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2733. Min Range: -5.2733
Max Act: 4.6170. Min Act: -0.1700
Data Index: 8043365 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19