Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2344 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3032. Min Range: -5.3032
Max Act: 5.3032. Min Act: -0.1700
Data Index: 278732 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3032. Min Range: -5.3032
Max Act: 5.2720. Min Act: -0.1700
Data Index: 5339322 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3032. Min Range: -5.3032
Max Act: 5.2407. Min Act: -0.1700
Data Index: 1806588 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.9907. Min Act: -0.1700
Data Index: 5080818 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.9907. Min Act: -0.1700
Data Index: 3043330 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.9595. Min Act: -0.1700
Data Index: 1806586 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.9282. Min Act: -0.1700
Data Index: 208993 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.8970. Min Act: -0.1700
Data Index: 1430353 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.8970. Min Act: -0.1700
Data Index: 1806584 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.8657. Min Act: -0.1700
Data Index: 2506489 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.8970. Min Act: -0.1700
Data Index: 3063837 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.8657. Min Act: -0.1700
Data Index: 3839144 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.8345. Min Act: -0.1700
Data Index: 6908379 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.8345. Min Act: -0.1700
Data Index: 7848309 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.8345. Min Act: -0.1700
Data Index: 7899927 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.8032. Min Act: -0.1700
Data Index: 2925436 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.7720. Min Act: -0.1700
Data Index: 4066778 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.7720. Min Act: -0.1700
Data Index: 7750095 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.7720. Min Act: -0.1700
Data Index: 2225522 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3032. Min Range: -5.3032
Max Act: 4.7720. Min Act: -0.1700
Data Index: 5747483 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19