Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3409 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.1668. Min Range: -1.1668
Max Act: 1.1668. Min Act: -0.0001
Data Index: 773756 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1668. Min Range: -1.1668
Max Act: 1.1271. Min Act: -0.0001
Data Index: 581464 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1668. Min Range: -1.1668
Max Act: 1.0003. Min Act: -0.0001
Data Index: 898874 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1668. Min Range: -1.1668
Max Act: 1.0545. Min Act: -0.0001
Data Index: 1309806 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1668. Min Range: -1.1668
Max Act: 1.0005. Min Act: -0.0001
Data Index: 1129506 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1668. Min Range: -1.1668
Max Act: 1.0651. Min Act: -0.0001
Data Index: 1125442 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9696. Min Act: -0.0001
Data Index: 949292 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1668. Min Range: -1.1668
Max Act: 1.0013. Min Act: -0.0001
Data Index: 783550 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9650. Min Act: -0.0001
Data Index: 1123428 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9638. Min Act: -0.0001
Data Index: 117097 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1668. Min Range: -1.1668
Max Act: 1.0214. Min Act: -0.0001
Data Index: 1141476 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9833. Min Act: -0.0001
Data Index: 1133163 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1668. Min Range: -1.1668
Max Act: 1.0435. Min Act: -0.0001
Data Index: 978743 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9151. Min Act: -0.0001
Data Index: 937435 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9834. Min Act: -0.0001
Data Index: 63995 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9473. Min Act: -0.0001
Data Index: 1052591 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9673. Min Act: -0.0001
Data Index: 350822 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9394. Min Act: -0.0001
Data Index: 192129 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9580. Min Act: -0.0001
Data Index: 1097359 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1668. Min Range: -1.1668
Max Act: 0.9537. Min Act: -0.0001
Data Index: 453264 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19