Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 595 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.6903. Min Act: -0.0001
Data Index: 1628996 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.6771. Min Act: -0.0001
Data Index: 1376182 (Python Code)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.4686. Min Act: -0.0001
Data Index: 1554577 (Python Code)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.6225. Min Act: -0.0001
Data Index: 1569093 (Python Code)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.4152. Min Act: -0.0001
Data Index: 1566647 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.4733. Min Act: -0.0001
Data Index: 1489134 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.4614. Min Act: -0.0001
Data Index: 1530477 (Python Code)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.4373. Min Act: -0.0001
Data Index: 1610372 (Python Code)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.3859. Min Act: -0.0001
Data Index: 1451561 (Python Code)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.3991. Min Act: -0.0001
Data Index: 1409168 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.5109. Min Act: -0.0001
Data Index: 1446270 (Python Code)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.5330. Min Act: -0.0001
Data Index: 1395660 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.4092. Min Act: -0.0001
Data Index: 1508886 (Python Code)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.3736. Min Act: -0.0001
Data Index: 1550356 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.3686. Min Act: -0.0001
Data Index: 1597214 (Python Code)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.4898. Min Act: -0.0001
Data Index: 1387282 (Python Code)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.2518. Min Act: -0.0001
Data Index: 1589531 (Python Code)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.1671. Min Act: -0.0001
Data Index: 1550720 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.1448. Min Act: -0.0001
Data Index: 1546090 (Python Code)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6903. Min Range: -2.6903
Max Act: 2.2280. Min Act: -0.0001
Data Index: 1507544 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19