Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3904 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.8048. Min Act: -0.1700
Data Index: 1950290 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.8048. Min Act: -0.1700
Data Index: 7782174 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.8048. Min Act: -0.1700
Data Index: 4484769 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.7735. Min Act: -0.1700
Data Index: 2862237 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.7735. Min Act: -0.1700
Data Index: 7930837 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.7735. Min Act: -0.1700
Data Index: 7774332 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.6173. Min Act: -0.1700
Data Index: 7927791 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.5860. Min Act: -0.1700
Data Index: 3305578 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.5548. Min Act: -0.1700
Data Index: 5648586 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.5860. Min Act: -0.1700
Data Index: 3516834 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.5235. Min Act: -0.1700
Data Index: 7089187 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.5548. Min Act: -0.1700
Data Index: 5033781 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.5235. Min Act: -0.1700
Data Index: 4371480 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.5235. Min Act: -0.1700
Data Index: 3634620 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.5235. Min Act: -0.1700
Data Index: 5923789 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.4923. Min Act: -0.1700
Data Index: 1032873 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.4923. Min Act: -0.1700
Data Index: 460587 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.4923. Min Act: -0.1700
Data Index: 1962750 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.4923. Min Act: -0.1700
Data Index: 2225205 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8048. Min Range: -6.8048
Max Act: 6.4298. Min Act: -0.1700
Data Index: 7230766 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19