Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4286 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.7863. Min Act: -0.0001
Data Index: 523988 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0127. Min Range: -4.0127
Max Act: 4.0127. Min Act: -0.0001
Data Index: 1178856 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.9208. Min Act: -0.0001
Data Index: 1098929 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.8190. Min Act: -0.0001
Data Index: 464335 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.6598. Min Act: -0.0001
Data Index: 1065640 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.4833. Min Act: -0.0001
Data Index: 42415 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0127. Min Range: -4.0127
Max Act: 2.9739. Min Act: -0.0001
Data Index: 635483 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.1169. Min Act: -0.0001
Data Index: 122438 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0127. Min Range: -4.0127
Max Act: 2.8254. Min Act: -0.0001
Data Index: 78857 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.0643. Min Act: -0.0001
Data Index: 810352 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.0674. Min Act: -0.0001
Data Index: 653214 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.0143. Min Act: -0.0001
Data Index: 1153881 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0127. Min Range: -4.0127
Max Act: 2.4325. Min Act: -0.0001
Data Index: 1325678 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.2334. Min Act: -0.0001
Data Index: 20735 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.2141. Min Act: -0.0001
Data Index: 81359 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0127. Min Range: -4.0127
Max Act: 2.6380. Min Act: -0.0001
Data Index: 1336183 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.0347. Min Act: -0.0001
Data Index: 320514 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0127. Min Range: -4.0127
Max Act: 2.9972. Min Act: -0.0001
Data Index: 196908 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0127. Min Range: -4.0127
Max Act: 2.0239. Min Act: -0.0001
Data Index: 1224477 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0127. Min Range: -4.0127
Max Act: 3.0450. Min Act: -0.0001
Data Index: 326779 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19