Model: None
Dataset: The Pile
Neuron 3276 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.6553. Min Act: -0.1700
Data Index: 2221647 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.6083. Min Act: -0.1700
Data Index: 1686986 (The Pile)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.6083. Min Act: -0.1700
Data Index: 9713494 (The Pile)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.4987. Min Act: -0.1700
Data Index: 1582846 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.4203. Min Act: -0.1700
Data Index: 9798769 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.4203. Min Act: -0.1700
Data Index: 2125830 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.4046. Min Act: -0.1700
Data Index: 10425140 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.3575. Min Act: -0.1700
Data Index: 4119147 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.3418. Min Act: -0.1700
Data Index: 790863 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.3261. Min Act: -0.1700
Data Index: 7312709 (The Pile)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.3261. Min Act: -0.1700
Data Index: 2705451 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.3104. Min Act: -0.1700
Data Index: 2192416 (The Pile)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.3104. Min Act: -0.1700
Data Index: 9315055 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.3104. Min Act: -0.1700
Data Index: 5047842 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.3104. Min Act: -0.1700
Data Index: 2708331 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.3104. Min Act: -0.1700
Data Index: 956278 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.2947. Min Act: -0.1700
Data Index: 6340138 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.2947. Min Act: -0.1700
Data Index: 5563667 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.2947. Min Act: -0.1700
Data Index: 3330056 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6553. Min Range: -3.6553
Max Act: 3.2790. Min Act: -0.1700
Data Index: 6328114 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19