Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 490 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1217. Min Range: -4.1217
Max Act: 4.1217. Min Act: -0.1700
Data Index: 7322994 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1217. Min Range: -4.1217
Max Act: 4.0592. Min Act: -0.1700
Data Index: 8489799 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9967. Min Act: -0.1700
Data Index: 6243362 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1217. Min Range: -4.1217
Max Act: 4.0279. Min Act: -0.1700
Data Index: 7914434 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1217. Min Range: -4.1217
Max Act: 4.0279. Min Act: -0.1700
Data Index: 975850 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9967. Min Act: -0.1700
Data Index: 2205074 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9654. Min Act: -0.1700
Data Index: 4881034 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9967. Min Act: -0.1700
Data Index: 2227897 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9342. Min Act: -0.1700
Data Index: 4774828 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9654. Min Act: -0.1700
Data Index: 4489433 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9342. Min Act: -0.1700
Data Index: 4944255 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9342. Min Act: -0.1700
Data Index: 1431015 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9342. Min Act: -0.1700
Data Index: 740098 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9029. Min Act: -0.1700
Data Index: 5832002 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9029. Min Act: -0.1700
Data Index: 3974769 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.9029. Min Act: -0.1700
Data Index: 6616628 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.8716. Min Act: -0.1700
Data Index: 3794563 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.8716. Min Act: -0.1700
Data Index: 3895123 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.8716. Min Act: -0.1700
Data Index: 7732762 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1217. Min Range: -4.1217
Max Act: 3.8404. Min Act: -0.1700
Data Index: 2037145 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19