Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4284 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.9260. Min Act: -0.1700
Data Index: 5032212 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.7385. Min Act: -0.1700
Data Index: 7814856 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.5510. Min Act: -0.1700
Data Index: 8551515 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.5510. Min Act: -0.1700
Data Index: 5687040 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.4885. Min Act: -0.1700
Data Index: 7439343 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 7062539 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 7652367 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 5847751 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 3453968 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 5159349 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 4687708 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 8407926 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 1068977 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.4260. Min Act: -0.1700
Data Index: 5196724 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.3635. Min Act: -0.1700
Data Index: 1625623 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.3635. Min Act: -0.1700
Data Index: 4646283 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.3635. Min Act: -0.1700
Data Index: 7509032 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.3322. Min Act: -0.1700
Data Index: 3672659 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.3322. Min Act: -0.1700
Data Index: 3822036 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9260. Min Range: -7.9260
Max Act: 7.3322. Min Act: -0.1700
Data Index: 6926831 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19