Model: None
Dataset: The Pile
Neuron 705 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 8.5078. Min Range: -8.5078
Max Act: 8.5078. Min Act: -0.1671
Data Index: 4095226 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5078. Min Range: -8.5078
Max Act: 8.0078. Min Act: -0.1159
Data Index: 7155513 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5078. Min Range: -8.5078
Max Act: 8.0078. Min Act: 0.0526
Data Index: 10197321 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.9140. Min Act: -0.1311
Data Index: 2026665 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.9140. Min Act: -0.1621
Data Index: 6267102 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.8515. Min Act: -0.0892
Data Index: 7339660 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.8203. Min Act: -0.1377
Data Index: 7689855 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.8203. Min Act: -0.0942
Data Index: 6456090 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5078. Min Range: -8.5078
Max Act: 8.0078. Min Act: -0.0852
Data Index: 8651965 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.8203. Min Act: -0.0930
Data Index: 9413341 (The Pile)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.8828. Min Act: 0.0781
Data Index: 1800052 (The Pile)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.9140. Min Act: -0.1344
Data Index: 2359281 (The Pile)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.7578. Min Act: -0.1335
Data Index: 10409277 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.6640. Min Act: 0.0222
Data Index: 483736 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.8203. Min Act: -0.1405
Data Index: 4010390 (The Pile)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.6640. Min Act: 0.0781
Data Index: 2417213 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.7578. Min Act: -0.1050
Data Index: 4521884 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.6953. Min Act: -0.1521
Data Index: 250910 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.7578. Min Act: -0.1690
Data Index: 1207948 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5078. Min Range: -8.5078
Max Act: 7.6953. Min Act: -0.1675
Data Index: 7811048 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19