Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2383 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.3439. Min Range: -3.3439
Max Act: 3.3439. Min Act: -0.0001
Data Index: 243967 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.9374. Min Act: -0.0001
Data Index: 1248637 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.8135. Min Act: -0.0001
Data Index: 943116 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.6103. Min Act: -0.0001
Data Index: 695495 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.5821. Min Act: -0.0001
Data Index: 633176 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.4437. Min Act: -0.0001
Data Index: 683456 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.6541. Min Act: -0.0001
Data Index: 601468 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.5177. Min Act: -0.0001
Data Index: 889262 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.6168. Min Act: -0.0001
Data Index: 680216 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.5920. Min Act: -0.0001
Data Index: 838338 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.5564. Min Act: -0.0001
Data Index: 270150 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.5388. Min Act: -0.0001
Data Index: 789195 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.4809. Min Act: -0.0001
Data Index: 890240 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.0622. Min Act: -0.0001
Data Index: 1282707 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.2765. Min Act: -0.0001
Data Index: 796012 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.4127. Min Act: -0.0001
Data Index: 279690 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.3916. Min Act: -0.0001
Data Index: 1158528 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.2424. Min Act: -0.0001
Data Index: 895164 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.2199. Min Act: -0.0001
Data Index: 373535 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3439. Min Range: -3.3439
Max Act: 2.5408. Min Act: -0.0001
Data Index: 187889 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19