Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2719 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.5652. Min Act: -0.1700
Data Index: 6737291 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.4712. Min Act: -0.1700
Data Index: 6669099 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.3615. Min Act: -0.1700
Data Index: 1587788 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2673. Min Act: -0.1700
Data Index: 519734 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2673. Min Act: -0.1700
Data Index: 8391189 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2673. Min Act: -0.1700
Data Index: 8250639 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2516. Min Act: -0.1700
Data Index: 2161777 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2673. Min Act: -0.1700
Data Index: 4832785 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2359. Min Act: -0.1700
Data Index: 1582310 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2359. Min Act: -0.1700
Data Index: 5508 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2202. Min Act: -0.1700
Data Index: 7224609 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2045. Min Act: -0.1700
Data Index: 215523 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2359. Min Act: -0.1700
Data Index: 5220372 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2202. Min Act: -0.1700
Data Index: 3511392 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2045. Min Act: -0.1700
Data Index: 4260035 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.2045. Min Act: -0.1700
Data Index: 1202901 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.1887. Min Act: -0.1700
Data Index: 2111352 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.1887. Min Act: -0.1700
Data Index: 4574465 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.1887. Min Act: -0.1700
Data Index: 8146728 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5652. Min Range: -3.5652
Max Act: 3.1887. Min Act: -0.1700
Data Index: 4187689 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19