Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1338. Min Range: -4.1338
Max Act: 4.1338. Min Act: -0.1700
Data Index: 4076417 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1338. Min Range: -4.1338
Max Act: 4.0401. Min Act: -0.1700
Data Index: 6140030 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1338. Min Range: -4.1338
Max Act: 4.0401. Min Act: -0.1700
Data Index: 196892 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1338. Min Range: -4.1338
Max Act: 4.0244. Min Act: -0.1700
Data Index: 3455167 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1338. Min Range: -4.1338
Max Act: 4.0088. Min Act: -0.1700
Data Index: 7118151 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9776. Min Act: -0.1700
Data Index: 8484634 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9932. Min Act: -0.1700
Data Index: 7826706 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9932. Min Act: -0.1700
Data Index: 1794805 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9776. Min Act: -0.1700
Data Index: 6773922 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9932. Min Act: -0.1700
Data Index: 877815 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9619. Min Act: -0.1700
Data Index: 8595708 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9619. Min Act: -0.1700
Data Index: 3538025 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9619. Min Act: -0.1700
Data Index: 1163589 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9463. Min Act: -0.1700
Data Index: 4337772 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9307. Min Act: -0.1700
Data Index: 3842083 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9307. Min Act: -0.1700
Data Index: 2704389 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9307. Min Act: -0.1700
Data Index: 2350776 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9307. Min Act: -0.1700
Data Index: 5224653 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9307. Min Act: -0.1700
Data Index: 718159 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1338. Min Range: -4.1338
Max Act: 3.9307. Min Act: -0.1700
Data Index: 679756 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19