Model: None
Dataset: The Pile
Neuron 1823 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.1126. Min Range: -3.1126
Max Act: 3.1126. Min Act: -0.1700
Data Index: 9876956 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1126. Min Range: -3.1126
Max Act: 3.0495. Min Act: -0.1700
Data Index: 10109436 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.9863. Min Act: -0.1700
Data Index: 9503188 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.9546. Min Act: -0.1700
Data Index: 9753159 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.9546. Min Act: -0.1700
Data Index: 9276918 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.9388. Min Act: -0.1700
Data Index: 5390917 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.9229. Min Act: -0.1700
Data Index: 7644767 (The Pile)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.9229. Min Act: -0.1700
Data Index: 1679593 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.9071. Min Act: -0.1700
Data Index: 8656167 (The Pile)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8754. Min Act: -0.1700
Data Index: 5174541 (The Pile)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8754. Min Act: -0.1700
Data Index: 5245010 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8754. Min Act: -0.1700
Data Index: 8234632 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8754. Min Act: -0.1700
Data Index: 9495067 (The Pile)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8754. Min Act: -0.1700
Data Index: 980591 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8754. Min Act: -0.1700
Data Index: 9559803 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8595. Min Act: -0.1700
Data Index: 9266390 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8595. Min Act: -0.1700
Data Index: 7749100 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8436. Min Act: -0.1700
Data Index: 4073186 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8436. Min Act: -0.1700
Data Index: 4079045 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1126. Min Range: -3.1126
Max Act: 2.8277. Min Act: -0.1700
Data Index: 6201157 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19