Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2364. Min Range: -8.2364
Max Act: 8.2364. Min Act: -0.1700
Data Index: 5561216 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2364. Min Range: -8.2364
Max Act: 8.1739. Min Act: -0.1700
Data Index: 625494 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2364. Min Range: -8.2364
Max Act: 8.1114. Min Act: -0.1700
Data Index: 2252188 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.9864. Min Act: -0.1700
Data Index: 7979762 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.9864. Min Act: -0.1700
Data Index: 4713176 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.9864. Min Act: -0.1700
Data Index: 4993337 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.9239. Min Act: -0.1700
Data Index: 6516274 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.8614. Min Act: -0.1700
Data Index: 2149786 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.8614. Min Act: -0.1700
Data Index: 5164010 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.8614. Min Act: -0.1700
Data Index: 1643031 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.8614. Min Act: -0.1700
Data Index: 1287852 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.7364. Min Act: -0.1700
Data Index: 756966 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.7989. Min Act: -0.1700
Data Index: 3156292 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.7364. Min Act: -0.1700
Data Index: 960489 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.7989. Min Act: -0.1700
Data Index: 1840816 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.7364. Min Act: -0.1700
Data Index: 2528777 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.7364. Min Act: -0.1700
Data Index: 2018892 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.8614. Min Act: -0.1700
Data Index: 6918268 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.7989. Min Act: -0.1700
Data Index: 2613187 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2364. Min Range: -8.2364
Max Act: 7.7364. Min Act: -0.1700
Data Index: 5411972 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19