Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1114 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.4680. Min Act: -0.0001
Data Index: 569598 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.4773. Min Act: -0.0001
Data Index: 1308301 (The Pile)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.3070. Min Act: -0.0001
Data Index: 1301813 (The Pile)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.2818. Min Act: -0.0001
Data Index: 1465971 (The Pile)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.2385. Min Act: -0.0001
Data Index: 1800757 (The Pile)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1601. Min Act: -0.0001
Data Index: 763175 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1492. Min Act: -0.0001
Data Index: 1729402 (The Pile)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1468. Min Act: -0.0001
Data Index: 567 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1628. Min Act: -0.0001
Data Index: 841867 (The Pile)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1296. Min Act: -0.0001
Data Index: 336407 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.0589. Min Act: -0.0001
Data Index: 1173279 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1391. Min Act: -0.0001
Data Index: 1828616 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1257. Min Act: -0.0001
Data Index: 1557398 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1605. Min Act: -0.0001
Data Index: 1408958 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1206. Min Act: -0.0001
Data Index: 63605 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1148. Min Act: -0.0001
Data Index: 963467 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1145. Min Act: -0.0001
Data Index: 852636 (The Pile)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1430. Min Act: -0.0001
Data Index: 756726 (The Pile)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.1065. Min Act: -0.0001
Data Index: 1954602 (The Pile)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4773. Min Range: -1.4773
Max Act: 1.0317. Min Act: -0.0001
Data Index: 952503 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19