Model: None
Dataset: The Pile
Neuron 394 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 4.2226. Min Range: -4.2226
Max Act: 4.2226. Min Act: -0.1700
Data Index: 2169731 (The Pile)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.9725. Min Act: -0.1700
Data Index: 5779232 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.6910. Min Act: -0.1700
Data Index: 4149720 (The Pile)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.7536. Min Act: -0.1700
Data Index: 3011381 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.7849. Min Act: -0.1700
Data Index: 4028731 (The Pile)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.3463. Min Act: -0.1700
Data Index: 5676538 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.7536. Min Act: -0.1700
Data Index: 9328728 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.6597. Min Act: -0.1700
Data Index: 5910060 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.7223. Min Act: -0.1700
Data Index: 5107893 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.7536. Min Act: -0.1700
Data Index: 6103212 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.5658. Min Act: -0.1700
Data Index: 7197651 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.2835. Min Act: -0.1700
Data Index: 4513739 (The Pile)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.5658. Min Act: -0.1686
Data Index: 7269271 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.6910. Min Act: -0.1700
Data Index: 3020053 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.6910. Min Act: -0.1700
Data Index: 6003470 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.5344. Min Act: -0.1700
Data Index: 1098555 (The Pile)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.5031. Min Act: -0.1697
Data Index: 9780762 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.6284. Min Act: -0.1700
Data Index: 4641236 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.5031. Min Act: -0.1700
Data Index: 746276 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2226. Min Range: -4.2226
Max Act: 3.4404. Min Act: -0.1700
Data Index: 10443251 (The Pile)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19