Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1887 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.6698. Min Act: -0.0001
Data Index: 332537 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.5484. Min Act: -0.0001
Data Index: 432358 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.5406. Min Act: -0.0001
Data Index: 430156 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.5194. Min Act: -0.0001
Data Index: 1494474 (Python Code)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.3910. Min Act: -0.0001
Data Index: 951282 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.2641. Min Act: -0.0001
Data Index: 1164475 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.2064. Min Act: -0.0001
Data Index: 1157880 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.3269. Min Act: -0.0001
Data Index: 1163595 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.4484. Min Act: -0.0001
Data Index: 769273 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.2668. Min Act: -0.0001
Data Index: 551412 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.2653. Min Act: -0.0001
Data Index: 468942 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.2643. Min Act: -0.0001
Data Index: 1281866 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.2370. Min Act: -0.0001
Data Index: 1420768 (Python Code)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.1604. Min Act: -0.0001
Data Index: 948662 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.2146. Min Act: -0.0001
Data Index: 940492 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.0992. Min Act: -0.0001
Data Index: 423917 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.0885. Min Act: -0.0001
Data Index: 1238986 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.3262. Min Act: -0.0001
Data Index: 619961 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.2085. Min Act: -0.0001
Data Index: 271298 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6698. Min Range: -2.6698
Max Act: 2.2020. Min Act: -0.0001
Data Index: 296066 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19