Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 769 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2012. Min Range: -8.2012
Max Act: 8.2012. Min Act: -0.1700
Data Index: 1667159 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2012. Min Range: -8.2012
Max Act: 8.0762. Min Act: -0.1700
Data Index: 1376666 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2012. Min Range: -8.2012
Max Act: 8.1387. Min Act: -0.1700
Data Index: 8782009 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2012. Min Range: -8.2012
Max Act: 8.0762. Min Act: -0.1700
Data Index: 2053957 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2012. Min Range: -8.2012
Max Act: 8.0137. Min Act: -0.1700
Data Index: 412708 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.9825. Min Act: -0.1700
Data Index: 8019192 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.8887. Min Act: -0.1700
Data Index: 1568851 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.9512. Min Act: -0.1700
Data Index: 8787314 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.8262. Min Act: -0.1700
Data Index: 7568560 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.7637. Min Act: -0.1700
Data Index: 2735371 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.7637. Min Act: -0.1700
Data Index: 5144045 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.7637. Min Act: -0.1700
Data Index: 6249289 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.6700. Min Act: -0.1700
Data Index: 7368108 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.5762. Min Act: -0.1700
Data Index: 6196066 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.6075. Min Act: -0.1700
Data Index: 7399498 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.5762. Min Act: -0.1700
Data Index: 1465247 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.5450. Min Act: -0.1700
Data Index: 7165824 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.4200. Min Act: -0.1700
Data Index: 2532077 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.4512. Min Act: -0.1700
Data Index: 934784 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2012. Min Range: -8.2012
Max Act: 7.3575. Min Act: -0.1700
Data Index: 8151428 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19