Model: None
Dataset: The Pile
Neuron 600 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.9356. Min Act: -0.1700
Data Index: 832380 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.9039. Min Act: -0.1700
Data Index: 9245471 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8722. Min Act: -0.1700
Data Index: 2185990 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8722. Min Act: -0.1700
Data Index: 1286204 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8404. Min Act: -0.1700
Data Index: 390512 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8404. Min Act: -0.1700
Data Index: 6783786 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8245. Min Act: -0.1700
Data Index: 5411279 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8245. Min Act: -0.1700
Data Index: 10584738 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8245. Min Act: -0.1700
Data Index: 7477247 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8245. Min Act: -0.1700
Data Index: 2992376 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8086. Min Act: -0.1700
Data Index: 5660618 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8086. Min Act: -0.1700
Data Index: 2756809 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.8086. Min Act: -0.1700
Data Index: 4735867 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.7926. Min Act: -0.1700
Data Index: 6224227 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.7926. Min Act: -0.1700
Data Index: 7787254 (The Pile)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.7926. Min Act: -0.1700
Data Index: 3438089 (The Pile)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.7926. Min Act: -0.1700
Data Index: 8705965 (The Pile)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.7926. Min Act: -0.1700
Data Index: 8771020 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.7767. Min Act: -0.1700
Data Index: 3131416 (The Pile)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9356. Min Range: -2.9356
Max Act: 2.7767. Min Act: -0.1700
Data Index: 7343187 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19