Model: None
Dataset: The Pile
Neuron 1928 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 6.7800. Min Range: -6.7800
Max Act: 5.9675. Min Act: -0.1700
Data Index: 8701547 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.4675. Min Act: -0.1700
Data Index: 9153891 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7800. Min Range: -6.7800
Max Act: 5.7487. Min Act: -0.1700
Data Index: 5358813 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.4987. Min Act: -0.1700
Data Index: 4245452 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.7800. Min Act: -0.1700
Data Index: 8248168 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.3425. Min Act: -0.1700
Data Index: 4094756 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7800. Min Range: -6.7800
Max Act: 5.2800. Min Act: -0.1700
Data Index: 159202 (The Pile)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.2800. Min Act: -0.1700
Data Index: 10273165 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7800. Min Range: -6.7800
Max Act: 5.9362. Min Act: -0.1700
Data Index: 6803943 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.2487. Min Act: -0.1700
Data Index: 10280711 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.4050. Min Act: -0.1700
Data Index: 8967702 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7800. Min Range: -6.7800
Max Act: 5.8112. Min Act: -0.1700
Data Index: 10727865 (The Pile)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.1550. Min Act: -0.1699
Data Index: 5237534 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.2175. Min Act: -0.1700
Data Index: 876174 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7800. Min Range: -6.7800
Max Act: 5.8737. Min Act: -0.1700
Data Index: 6975759 (The Pile)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.1237. Min Act: -0.1699
Data Index: 8042175 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.2800. Min Act: -0.1700
Data Index: 5210281 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.2175. Min Act: -0.1700
Data Index: 1994106 (The Pile)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7800. Min Range: -6.7800
Max Act: 6.0612. Min Act: -0.1699
Data Index: 6458429 (The Pile)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7800. Min Range: -6.7800
Max Act: 5.9675. Min Act: -0.1700
Data Index: 2466105 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19