Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1786 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.8267. Min Act: -0.1700
Data Index: 2647397 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7751. Min Act: -0.1700
Data Index: 6710144 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.8010. Min Act: -0.1700
Data Index: 1163860 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7837. Min Act: -0.1693
Data Index: 7457235 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7837. Min Act: -0.1700
Data Index: 2439820 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7320. Min Act: -0.1700
Data Index: 4257689 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7320. Min Act: -0.1700
Data Index: 1882763 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7320. Min Act: -0.1700
Data Index: 4766309 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7320. Min Act: -0.1700
Data Index: 3431504 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7233. Min Act: -0.1700
Data Index: 4296677 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7146. Min Act: -0.1700
Data Index: 5552758 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7146. Min Act: -0.1700
Data Index: 3473936 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7146. Min Act: -0.1700
Data Index: 6745841 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7060. Min Act: -0.1700
Data Index: 8457652 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7060. Min Act: -0.1700
Data Index: 6194318 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7060. Min Act: -0.1700
Data Index: 1609822 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7060. Min Act: -0.1700
Data Index: 8293432 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7233. Min Act: -0.1700
Data Index: 664408 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7146. Min Act: -0.1700
Data Index: 4245142 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8267. Min Range: -1.8267
Max Act: 1.7060. Min Act: -0.1700
Data Index: 5431447 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19