Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 6
Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')
Click the toggle to see the full text!
Text #0
Max Range: 6.1271. Min Range: -6.1271
Max Act: 6.1271. Min Act: -0.1700
Data Index: 5115022 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9664. Min Act: -0.1700
Data Index: 5022475 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9369. Min Act: -0.1700
Data Index: 2282992 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9191. Min Act: -0.1700
Data Index: 3367444 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9756. Min Act: -0.1700
Data Index: 1514975 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8903. Min Act: -0.1700
Data Index: 3674292 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8939. Min Act: -0.1700
Data Index: 1459306 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8881. Min Act: -0.1700
Data Index: 7875311 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9045. Min Act: -0.1700
Data Index: 4334484 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8986. Min Act: -0.1700
Data Index: 3941468 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8750. Min Act: -0.1700
Data Index: 4950580 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8750. Min Act: -0.1700
Data Index: 3426267 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8744. Min Act: -0.1700
Data Index: 6778746 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8380. Min Act: -0.1700
Data Index: 7027973 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8289. Min Act: -0.1700
Data Index: 3895815 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8270. Min Act: -0.1700
Data Index: 6425517 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8584. Min Act: -0.1700
Data Index: 4537412 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8549. Min Act: -0.1700
Data Index: 2493929 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8639. Min Act: -0.1700
Data Index: 8702358 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8762. Min Act: -0.1700
Data Index: 1953910 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full textTruncated
Full Text #19