Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2172 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.7297. Min Act: -0.0001
Data Index: 52445 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.7979. Min Act: -0.0001
Data Index: 922111 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.5846. Min Act: -0.0001
Data Index: 96587 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.6576. Min Act: -0.0001
Data Index: 234432 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.8845. Min Act: -0.0001
Data Index: 789411 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.7581. Min Act: -0.0001
Data Index: 636064 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.6214. Min Act: -0.0001
Data Index: 130709 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.7289. Min Act: -0.0001
Data Index: 982670 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.4650. Min Act: -0.0001
Data Index: 43396 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.8127. Min Act: -0.0001
Data Index: 1140273 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.6832. Min Act: -0.0001
Data Index: 724381 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.3941. Min Act: -0.0001
Data Index: 693238 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.6382. Min Act: -0.0001
Data Index: 553634 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.3766. Min Act: -0.0001
Data Index: 52826 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.7407. Min Act: -0.0001
Data Index: 1302503 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.6053. Min Act: -0.0001
Data Index: 349198 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.7239. Min Act: -0.0001
Data Index: 699747 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.7132. Min Act: -0.0001
Data Index: 353087 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.4681. Min Act: -0.0001
Data Index: 1220669 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8845. Min Range: -2.8845
Max Act: 2.5671. Min Act: -0.0001
Data Index: 1193170 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19