Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1265 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.7190. Min Act: -0.1700
Data Index: 1744611 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.6565. Min Act: -0.1700
Data Index: 5445100 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.5940. Min Act: -0.1700
Data Index: 1416327 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.5940. Min Act: -0.1700
Data Index: 1488946 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.4690. Min Act: -0.1700
Data Index: 1202704 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.5315. Min Act: -0.1700
Data Index: 5665253 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.4690. Min Act: -0.1700
Data Index: 4502588 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.5315. Min Act: -0.1700
Data Index: 5816100 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.5315. Min Act: -0.1700
Data Index: 132786 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.4690. Min Act: -0.1700
Data Index: 6842511 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.4065. Min Act: -0.1700
Data Index: 2230537 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.4690. Min Act: -0.1700
Data Index: 6451400 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.4065. Min Act: -0.1700
Data Index: 3901718 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.3440. Min Act: -0.1700
Data Index: 6777609 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.4065. Min Act: -0.1700
Data Index: 4220480 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.3440. Min Act: -0.1700
Data Index: 4516779 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.3440. Min Act: -0.1700
Data Index: 8098939 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.2815. Min Act: -0.1700
Data Index: 3265116 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.2815. Min Act: -0.1700
Data Index: 4211561 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7190. Min Range: -8.7190
Max Act: 8.2815. Min Act: -0.1700
Data Index: 7948875 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19