Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1453 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0767. Min Range: -2.0767
Max Act: 2.0767. Min Act: -0.1700
Data Index: 3128704 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9755. Min Act: -0.1700
Data Index: 3128709 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9755. Min Act: -0.1700
Data Index: 3128708 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9586. Min Act: -0.1700
Data Index: 8821172 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9586. Min Act: -0.1700
Data Index: 4926129 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9755. Min Act: -0.1700
Data Index: 4585483 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9755. Min Act: -0.1700
Data Index: 669730 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9501. Min Act: -0.1700
Data Index: 6727528 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9586. Min Act: -0.1700
Data Index: 3410743 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9331. Min Act: -0.1700
Data Index: 4132542 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9501. Min Act: -0.1700
Data Index: 1503147 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9416. Min Act: -0.1700
Data Index: 1986951 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9416. Min Act: -0.1700
Data Index: 8821177 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9331. Min Act: -0.1700
Data Index: 7538236 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9501. Min Act: -0.1700
Data Index: 5516669 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9416. Min Act: -0.1700
Data Index: 5010540 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9331. Min Act: -0.1700
Data Index: 5749274 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9246. Min Act: -0.1700
Data Index: 5749280 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9246. Min Act: -0.1700
Data Index: 1591591 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9246. Min Act: -0.1700
Data Index: 8567245 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19