Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4499 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.9388. Min Act: -0.0001
Data Index: 694863 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.8521. Min Act: -0.0001
Data Index: 1342693 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.9892. Min Act: -0.0001
Data Index: 575225 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.9325. Min Act: -0.0001
Data Index: 822467 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.6931. Min Act: -0.0001
Data Index: 282940 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.7389. Min Act: -0.0001
Data Index: 1073017 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.6268. Min Act: -0.0001
Data Index: 1183290 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.2732. Min Act: -0.0001
Data Index: 42437 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.3925. Min Act: -0.0001
Data Index: 1316293 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.5461. Min Act: -0.0001
Data Index: 468962 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.5818. Min Act: -0.0001
Data Index: 284497 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.2673. Min Act: -0.0001
Data Index: 877436 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.4295. Min Act: -0.0001
Data Index: 223669 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.3253. Min Act: -0.0001
Data Index: 1066621 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.2829. Min Act: -0.0001
Data Index: 663267 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.3489. Min Act: -0.0001
Data Index: 671650 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.3093. Min Act: -0.0001
Data Index: 45204 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.3739. Min Act: -0.0001
Data Index: 622118 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.1646. Min Act: -0.0001
Data Index: 461441 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9892. Min Range: -1.9892
Max Act: 1.2993. Min Act: -0.0001
Data Index: 102093 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19