Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3896 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.6175. Min Act: -0.0000
Data Index: 1640036 (Python Code)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.2289. Min Act: -0.0001
Data Index: 1439620 (Python Code)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.3224. Min Act: -0.0001
Data Index: 1364386 (Python Code)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.1462. Min Act: -0.0001
Data Index: 1370407 (Python Code)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.3457. Min Act: -0.0001
Data Index: 1609792 (Python Code)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.3493. Min Act: -0.0001
Data Index: 1626103 (Python Code)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.0067. Min Act: -0.0001
Data Index: 1426569 (Python Code)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.3345. Min Act: -0.0001
Data Index: 1399485 (Python Code)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.1123. Min Act: -0.0000
Data Index: 1479108 (Python Code)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6175. Min Range: -2.6175
Max Act: 1.9913. Min Act: -0.0001
Data Index: 1441427 (Python Code)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6175. Min Range: -2.6175
Max Act: 1.9696. Min Act: -0.0001
Data Index: 1400104 (Python Code)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6175. Min Range: -2.6175
Max Act: 1.7406. Min Act: -0.0001
Data Index: 230946 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.0380. Min Act: -0.0000
Data Index: 1553585 (Python Code)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6175. Min Range: -2.6175
Max Act: 2.1290. Min Act: -0.0000
Data Index: 1486747 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6175. Min Range: -2.6175
Max Act: 1.6918. Min Act: -0.0001
Data Index: 1179309 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6175. Min Range: -2.6175
Max Act: 1.7814. Min Act: -0.0001
Data Index: 949743 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6175. Min Range: -2.6175
Max Act: 1.8899. Min Act: -0.0001
Data Index: 349854 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6175. Min Range: -2.6175
Max Act: 1.9939. Min Act: -0.0001
Data Index: 1364485 (Python Code)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6175. Min Range: -2.6175
Max Act: 1.8745. Min Act: -0.0001
Data Index: 169263 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6175. Min Range: -2.6175
Max Act: 1.9062. Min Act: -0.0001
Data Index: 1433136 (Python Code)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19