Model: None
Dataset: The Pile
Neuron 2785 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.5702. Min Act: -0.1700
Data Index: 8864261 (The Pile)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.5545. Min Act: -0.1700
Data Index: 4939104 (The Pile)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.5389. Min Act: -0.1700
Data Index: 286249 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.5232. Min Act: -0.1700
Data Index: 957027 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.5232. Min Act: -0.1700
Data Index: 8682758 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.5075. Min Act: -0.1700
Data Index: 2035328 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.5075. Min Act: -0.1700
Data Index: 6135863 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4919. Min Act: -0.1700
Data Index: 7521217 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4919. Min Act: -0.1700
Data Index: 7798501 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4919. Min Act: -0.1700
Data Index: 8904209 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4919. Min Act: -0.1700
Data Index: 3998880 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4919. Min Act: -0.1700
Data Index: 3240854 (The Pile)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4919. Min Act: -0.1700
Data Index: 3470116 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4762. Min Act: -0.1700
Data Index: 5537437 (The Pile)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4762. Min Act: -0.1700
Data Index: 2638793 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4762. Min Act: -0.1700
Data Index: 5433538 (The Pile)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4762. Min Act: -0.1700
Data Index: 1141849 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4762. Min Act: -0.1700
Data Index: 4668420 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4762. Min Act: -0.1700
Data Index: 228031 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5702. Min Range: -3.5702
Max Act: 3.4762. Min Act: -0.1700
Data Index: 10739381 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19