Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 22 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 3.1720. Min Range: -3.1720
Max Act: 3.1720. Min Act: -0.0001
Data Index: 1991271 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1720. Min Range: -3.1720
Max Act: 3.1129. Min Act: -0.0001
Data Index: 774004 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1720. Min Range: -3.1720
Max Act: 3.0034. Min Act: -0.0001
Data Index: 1535054 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.9863. Min Act: -0.0001
Data Index: 1107504 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.9997. Min Act: -0.0001
Data Index: 704555 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1720. Min Range: -3.1720
Max Act: 3.1288. Min Act: -0.0001
Data Index: 1439231 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.9710. Min Act: -0.0001
Data Index: 1106588 (The Pile)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.9399. Min Act: -0.0001
Data Index: 963487 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.8974. Min Act: -0.0001
Data Index: 1277548 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1720. Min Range: -3.1720
Max Act: 3.0204. Min Act: -0.0001
Data Index: 2671 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.8786. Min Act: -0.0001
Data Index: 1455215 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.8838. Min Act: -0.0001
Data Index: 793678 (The Pile)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.9912. Min Act: -0.0001
Data Index: 478501 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.6813. Min Act: -0.0001
Data Index: 878208 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.7964. Min Act: -0.0001
Data Index: 106095 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.8373. Min Act: -0.0001
Data Index: 1410033 (The Pile)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.6717. Min Act: -0.0001
Data Index: 686306 (The Pile)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.6497. Min Act: -0.0001
Data Index: 489781 (The Pile)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.6288. Min Act: -0.0001
Data Index: 1733765 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1720. Min Range: -3.1720
Max Act: 2.6177. Min Act: -0.0001
Data Index: 1705139 (The Pile)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19