Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1939 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2822. Min Range: -6.2822
Max Act: 6.2822. Min Act: -0.1700
Data Index: 7150177 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2822. Min Range: -6.2822
Max Act: 6.2509. Min Act: -0.1700
Data Index: 1269938 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2822. Min Range: -6.2822
Max Act: 6.1572. Min Act: -0.1700
Data Index: 4402400 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2822. Min Range: -6.2822
Max Act: 6.0009. Min Act: -0.1700
Data Index: 8641611 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.9384. Min Act: -0.1700
Data Index: 1545186 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.8447. Min Act: -0.1700
Data Index: 6344962 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.7822. Min Act: -0.1700
Data Index: 569038 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.7509. Min Act: -0.1700
Data Index: 6013068 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.6884. Min Act: -0.1700
Data Index: 7742847 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.6572. Min Act: -0.1700
Data Index: 8044202 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.6572. Min Act: -0.1700
Data Index: 1510798 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.5947. Min Act: -0.1700
Data Index: 2050732 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.5947. Min Act: -0.1700
Data Index: 6403454 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.5634. Min Act: -0.1700
Data Index: 2454990 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.5322. Min Act: -0.1700
Data Index: 3599424 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.5322. Min Act: -0.1700
Data Index: 3672060 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.5322. Min Act: -0.1700
Data Index: 1341335 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.5322. Min Act: -0.1700
Data Index: 4464675 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.5322. Min Act: -0.1700
Data Index: 5590336 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2822. Min Range: -6.2822
Max Act: 5.5322. Min Act: -0.1700
Data Index: 8304251 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19