Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1991 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0266. Min Range: -8.0266
Max Act: 8.0266. Min Act: -0.1700
Data Index: 6948000 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.8391. Min Act: -0.1700
Data Index: 6776343 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.7766. Min Act: -0.1700
Data Index: 7551420 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.7766. Min Act: -0.1700
Data Index: 233544 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.3704. Min Act: -0.1700
Data Index: 4738689 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.2766. Min Act: -0.1700
Data Index: 2630312 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.3079. Min Act: -0.1700
Data Index: 7557893 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.1829. Min Act: -0.1700
Data Index: 2576631 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.1204. Min Act: -0.1700
Data Index: 703697 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.1829. Min Act: -0.1700
Data Index: 18055 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.1829. Min Act: -0.1700
Data Index: 4367235 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.1204. Min Act: -0.1700
Data Index: 4809563 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.0891. Min Act: -0.1700
Data Index: 6188299 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.0266. Min Act: -0.1700
Data Index: 1437166 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0266. Min Range: -8.0266
Max Act: 7.0266. Min Act: -0.1700
Data Index: 7298166 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0266. Min Range: -8.0266
Max Act: 6.9954. Min Act: -0.1700
Data Index: 8257597 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0266. Min Range: -8.0266
Max Act: 6.9641. Min Act: -0.1700
Data Index: 2689383 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0266. Min Range: -8.0266
Max Act: 6.9329. Min Act: -0.1700
Data Index: 5513125 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0266. Min Range: -8.0266
Max Act: 6.8704. Min Act: -0.1700
Data Index: 3324730 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0266. Min Range: -8.0266
Max Act: 6.8391. Min Act: -0.1700
Data Index: 1437689 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19