Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2512 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3811. Min Range: -1.3811
Max Act: 1.3811. Min Act: -0.0001
Data Index: 588388 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3811. Min Range: -1.3811
Max Act: 1.1875. Min Act: -0.0001
Data Index: 677836 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3811. Min Range: -1.3811
Max Act: 1.2227. Min Act: -0.0001
Data Index: 1078968 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3811. Min Range: -1.3811
Max Act: 1.0711. Min Act: -0.0001
Data Index: 698695 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3811. Min Range: -1.3811
Max Act: 1.0621. Min Act: -0.0001
Data Index: 374484 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3811. Min Range: -1.3811
Max Act: 1.0279. Min Act: -0.0001
Data Index: 619217 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3811. Min Range: -1.3811
Max Act: 1.0751. Min Act: -0.0001
Data Index: 121859 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3811. Min Range: -1.3811
Max Act: 1.0357. Min Act: -0.0001
Data Index: 1109280 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.9997. Min Act: -0.0001
Data Index: 873333 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.9998. Min Act: -0.0001
Data Index: 373171 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.9016. Min Act: -0.0001
Data Index: 1348367 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.9820. Min Act: -0.0001
Data Index: 162183 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.8372. Min Act: -0.0001
Data Index: 772032 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.8462. Min Act: -0.0001
Data Index: 1154384 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.8750. Min Act: -0.0001
Data Index: 267182 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.8760. Min Act: -0.0001
Data Index: 757844 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.8363. Min Act: -0.0001
Data Index: 375955 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.8795. Min Act: -0.0001
Data Index: 227292 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.8701. Min Act: -0.0001
Data Index: 758693 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3811. Min Range: -1.3811
Max Act: 0.8723. Min Act: -0.0001
Data Index: 760085 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19