Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 540 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.8220. Min Act: -0.0001
Data Index: 800404 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.4764. Min Act: -0.0001
Data Index: 1768259 (The Pile)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.4753. Min Act: -0.0001
Data Index: 1566415 (The Pile)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.2333. Min Act: -0.0001
Data Index: 570139 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.1957. Min Act: -0.0001
Data Index: 801171 (The Pile)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.2966. Min Act: -0.0001
Data Index: 1356329 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.1773. Min Act: -0.0001
Data Index: 1346776 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.2004. Min Act: -0.0001
Data Index: 183247 (The Pile)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.1506. Min Act: -0.0001
Data Index: 1235360 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.0893. Min Act: -0.0001
Data Index: 1900206 (The Pile)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.0602. Min Act: -0.0001
Data Index: 1521763 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.0525. Min Act: -0.0001
Data Index: 187517 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.1008. Min Act: -0.0001
Data Index: 1953361 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.1898. Min Act: -0.0001
Data Index: 105104 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.0419. Min Act: -0.0001
Data Index: 1310122 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.0891. Min Act: -0.0001
Data Index: 1844511 (The Pile)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.0210. Min Act: -0.0001
Data Index: 32258 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8220. Min Range: -1.8220
Max Act: 0.9230. Min Act: -0.0001
Data Index: 1421921 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.0427. Min Act: -0.0001
Data Index: 1824037 (The Pile)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8220. Min Range: -1.8220
Max Act: 1.0726. Min Act: -0.0001
Data Index: 717283 (The Pile)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19