Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1565 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.3427. Min Act: -0.1700
Data Index: 8083014 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.1239. Min Act: -0.1700
Data Index: 402641 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.0927. Min Act: -0.1700
Data Index: 4962212 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.0927. Min Act: -0.1700
Data Index: 1753576 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.0614. Min Act: -0.1700
Data Index: 4736128 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.0301. Min Act: -0.1700
Data Index: 4442679 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.0301. Min Act: -0.1700
Data Index: 7072079 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.0301. Min Act: -0.1700
Data Index: 8416378 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9989. Min Act: -0.1700
Data Index: 5692221 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9676. Min Act: -0.1700
Data Index: 1753577 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9364. Min Act: -0.1700
Data Index: 408102 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9676. Min Act: -0.1700
Data Index: 741786 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9676. Min Act: -0.1700
Data Index: 4808015 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9051. Min Act: -0.1700
Data Index: 5657208 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9364. Min Act: -0.1700
Data Index: 5168993 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9051. Min Act: -0.1700
Data Index: 8077207 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9051. Min Act: -0.1700
Data Index: 408105 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9051. Min Act: -0.1700
Data Index: 2320133 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.9364. Min Act: -0.1700
Data Index: 999259 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3427. Min Range: -4.3427
Max Act: 3.8738. Min Act: -0.1700
Data Index: 5862979 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19