Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 308 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2499. Min Range: -6.2499
Max Act: 6.2499. Min Act: -0.1700
Data Index: 18740 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2499. Min Range: -6.2499
Max Act: 6.1562. Min Act: -0.1700
Data Index: 6464076 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2499. Min Range: -6.2499
Max Act: 6.0937. Min Act: -0.1700
Data Index: 642539 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.9999. Min Act: -0.1700
Data Index: 834953 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.9687. Min Act: -0.1700
Data Index: 3202420 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.9687. Min Act: -0.1700
Data Index: 6327909 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.9062. Min Act: -0.1700
Data Index: 4878576 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.9062. Min Act: -0.1700
Data Index: 1239745 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.8749. Min Act: -0.1700
Data Index: 4858598 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.8749. Min Act: -0.1700
Data Index: 7791003 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.8124. Min Act: -0.1700
Data Index: 7238536 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.8437. Min Act: -0.1700
Data Index: 6672255 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.8124. Min Act: -0.1700
Data Index: 6972782 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.7812. Min Act: -0.1700
Data Index: 1824469 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.8124. Min Act: -0.1700
Data Index: 3190030 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.7812. Min Act: -0.1700
Data Index: 6373856 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.7812. Min Act: -0.1700
Data Index: 6983872 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.7812. Min Act: -0.1700
Data Index: 3578133 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.7812. Min Act: -0.1700
Data Index: 7538860 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2499. Min Range: -6.2499
Max Act: 5.7499. Min Act: -0.1700
Data Index: 831162 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19