Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 573 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0109. Min Range: -5.0109
Max Act: 5.0109. Min Act: -0.1700
Data Index: 5837994 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.9797. Min Act: -0.1700
Data Index: 2259221 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8547. Min Act: -0.1700
Data Index: 7079789 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8547. Min Act: -0.1700
Data Index: 6089393 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8547. Min Act: -0.1700
Data Index: 1201137 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8547. Min Act: -0.1700
Data Index: 5315679 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8234. Min Act: -0.1700
Data Index: 1552509 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8234. Min Act: -0.1700
Data Index: 1712997 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8234. Min Act: -0.1700
Data Index: 2297403 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.7609. Min Act: -0.1700
Data Index: 6365358 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6984. Min Act: -0.1700
Data Index: 7762299 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.7297. Min Act: -0.1700
Data Index: 7591474 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6984. Min Act: -0.1700
Data Index: 1216611 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6984. Min Act: -0.1700
Data Index: 6799397 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6984. Min Act: -0.1700
Data Index: 3093112 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6984. Min Act: -0.1700
Data Index: 3991101 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6984. Min Act: -0.1700
Data Index: 2323369 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6672. Min Act: -0.1700
Data Index: 4126104 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6672. Min Act: -0.1700
Data Index: 7047518 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6672. Min Act: -0.1700
Data Index: 5043661 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19