Model: None
Dataset: The Pile
Neuron 1854 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.4425. Min Act: -0.1700
Data Index: 4458493 (The Pile)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3954. Min Act: -0.1700
Data Index: 6841618 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3954. Min Act: -0.1700
Data Index: 4483127 (The Pile)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3484. Min Act: -0.1700
Data Index: 10570853 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3954. Min Act: -0.1700
Data Index: 6749564 (The Pile)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3327. Min Act: -0.1700
Data Index: 4851620 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3484. Min Act: -0.1700
Data Index: 10450193 (The Pile)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3484. Min Act: -0.1700
Data Index: 3538652 (The Pile)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3327. Min Act: -0.1700
Data Index: 10071098 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3484. Min Act: -0.1700
Data Index: 538311 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.2855. Min Act: -0.1700
Data Index: 3616142 (The Pile)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3640. Min Act: -0.1700
Data Index: 7164564 (The Pile)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3327. Min Act: -0.1700
Data Index: 4455475 (The Pile)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.2698. Min Act: -0.1700
Data Index: 5025828 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3170. Min Act: -0.1700
Data Index: 6443152 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.2855. Min Act: -0.1700
Data Index: 1172689 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3013. Min Act: -0.1700
Data Index: 2800223 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.3013. Min Act: -0.1700
Data Index: 6957565 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.2855. Min Act: -0.1700
Data Index: 6333195 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4425. Min Range: -3.4425
Max Act: 3.2855. Min Act: -0.1700
Data Index: 8910815 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19