Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3531 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.7149. Min Act: -0.0001
Data Index: 1588654 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.6751. Min Act: -0.0001
Data Index: 1418373 (Python Code)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.6847. Min Act: -0.0001
Data Index: 1427965 (Python Code)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.4828. Min Act: -0.0001
Data Index: 1411656 (Python Code)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.5793. Min Act: -0.0001
Data Index: 1456539 (Python Code)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.5893. Min Act: -0.0001
Data Index: 1382095 (Python Code)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.4396. Min Act: -0.0001
Data Index: 1616053 (Python Code)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.7048. Min Act: -0.0001
Data Index: 1505145 (Python Code)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.6909. Min Act: -0.0001
Data Index: 1539892 (Python Code)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.5508. Min Act: -0.0001
Data Index: 1369566 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.4390. Min Act: -0.0001
Data Index: 1477757 (Python Code)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.3090. Min Act: -0.0001
Data Index: 1381099 (Python Code)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.6968. Min Act: -0.0001
Data Index: 1603909 (Python Code)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.4233. Min Act: -0.0001
Data Index: 1376283 (Python Code)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.5557. Min Act: -0.0001
Data Index: 1489912 (Python Code)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.4007. Min Act: -0.0001
Data Index: 1599066 (Python Code)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.3911. Min Act: -0.0001
Data Index: 1441373 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.4919. Min Act: -0.0001
Data Index: 1516147 (Python Code)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.4797. Min Act: -0.0001
Data Index: 1451796 (Python Code)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7149. Min Range: -2.7149
Max Act: 2.4695. Min Act: -0.0001
Data Index: 1489681 (Python Code)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19