Model: None
Dataset: The Pile
Neuron 3940 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.8907. Min Act: -0.1700
Data Index: 8193771 (The Pile)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.8594. Min Act: -0.1700
Data Index: 4540733 (The Pile)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.8282. Min Act: -0.1699
Data Index: 4890085 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.8282. Min Act: -0.1700
Data Index: 2268743 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.8282. Min Act: -0.1700
Data Index: 10202659 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7969. Min Act: -0.1700
Data Index: 7968719 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7969. Min Act: -0.1700
Data Index: 3952411 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7657. Min Act: -0.1699
Data Index: 3040542 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7657. Min Act: -0.1700
Data Index: 8959523 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7657. Min Act: -0.1700
Data Index: 6301686 (The Pile)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7344. Min Act: -0.1700
Data Index: 2478811 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7344. Min Act: -0.1699
Data Index: 6268875 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7344. Min Act: -0.1700
Data Index: 3744272 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7344. Min Act: -0.1700
Data Index: 4465079 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7032. Min Act: -0.1700
Data Index: 1817510 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7032. Min Act: -0.1700
Data Index: 9485127 (The Pile)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7032. Min Act: -0.1700
Data Index: 7591444 (The Pile)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.7032. Min Act: -0.1700
Data Index: 3181529 (The Pile)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.6719. Min Act: -0.1700
Data Index: 8728415 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8907. Min Range: -4.8907
Max Act: 4.6719. Min Act: -0.1700
Data Index: 4974 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19