Model: None
Dataset: The Pile
Neuron 2812 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.6087. Min Act: -0.1700
Data Index: 8681284 (The Pile)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.5931. Min Act: -0.1700
Data Index: 3113869 (The Pile)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.4677. Min Act: -0.1700
Data Index: 4850296 (The Pile)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.4521. Min Act: -0.1700
Data Index: 8052080 (The Pile)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.4364. Min Act: -0.1696
Data Index: 558509 (The Pile)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.4207. Min Act: -0.1700
Data Index: 3765408 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.4050. Min Act: -0.1700
Data Index: 10372176 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.4050. Min Act: -0.1700
Data Index: 9576505 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.3893. Min Act: -0.1700
Data Index: 3836749 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.3580. Min Act: -0.1700
Data Index: 7870182 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.3423. Min Act: -0.1699
Data Index: 8353771 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.3266. Min Act: -0.1700
Data Index: 7173738 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.3266. Min Act: -0.1699
Data Index: 5557212 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.3266. Min Act: -0.1700
Data Index: 8389163 (The Pile)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.3109. Min Act: -0.1700
Data Index: 348014 (The Pile)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.3109. Min Act: -0.1700
Data Index: 6572833 (The Pile)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.2952. Min Act: -0.1700
Data Index: 10672211 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.2952. Min Act: -0.1700
Data Index: 672548 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.2952. Min Act: -0.1700
Data Index: 6910576 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6087. Min Range: -3.6087
Max Act: 3.2795. Min Act: -0.1700
Data Index: 2494512 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19