Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 838 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.2224. Min Act: -0.1700
Data Index: 7102536 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.1726. Min Act: -0.1700
Data Index: 3089096 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.1560. Min Act: -0.1700
Data Index: 1972477 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.1560. Min Act: -0.1700
Data Index: 253288 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.1393. Min Act: -0.1700
Data Index: 7803346 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.1226. Min Act: -0.1700
Data Index: 431636 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.1059. Min Act: -0.1700
Data Index: 2615604 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0891. Min Act: -0.1700
Data Index: 923318 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0724. Min Act: -0.1700
Data Index: 623022 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.1059. Min Act: -0.1700
Data Index: 4162725 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0891. Min Act: -0.1700
Data Index: 2901938 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0556. Min Act: -0.1700
Data Index: 5977514 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0724. Min Act: -0.1700
Data Index: 8556744 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0724. Min Act: -0.1700
Data Index: 2832552 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0891. Min Act: -0.1700
Data Index: 2241786 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0556. Min Act: -0.1700
Data Index: 90457 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0724. Min Act: -0.1700
Data Index: 4384691 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0556. Min Act: -0.1700
Data Index: 5296757 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0556. Min Act: -0.1700
Data Index: 6730938 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.0556. Min Act: -0.1700
Data Index: 6739399 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19