Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2807 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.3236. Min Range: -1.3236
Max Act: 1.2465. Min Act: -0.0001
Data Index: 1087906 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3236. Min Range: -1.3236
Max Act: 1.3236. Min Act: -0.0001
Data Index: 717333 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3236. Min Range: -1.3236
Max Act: 1.1527. Min Act: -0.0001
Data Index: 1177518 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3236. Min Range: -1.3236
Max Act: 1.0847. Min Act: -0.0001
Data Index: 614098 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3236. Min Range: -1.3236
Max Act: 1.0905. Min Act: -0.0001
Data Index: 134668 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3236. Min Range: -1.3236
Max Act: 1.0161. Min Act: -0.0001
Data Index: 283990 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.9861. Min Act: -0.0001
Data Index: 207591 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.9553. Min Act: -0.0001
Data Index: 687639 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.9818. Min Act: -0.0001
Data Index: 101919 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3236. Min Range: -1.3236
Max Act: 1.0403. Min Act: -0.0001
Data Index: 342025 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3236. Min Range: -1.3236
Max Act: 1.0054. Min Act: -0.0001
Data Index: 818858 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.9080. Min Act: -0.0001
Data Index: 1228802 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.9920. Min Act: -0.0001
Data Index: 52086 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.9062. Min Act: -0.0001
Data Index: 380562 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.9044. Min Act: -0.0001
Data Index: 152044 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.9183. Min Act: -0.0001
Data Index: 874074 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.9449. Min Act: -0.0001
Data Index: 615454 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.8698. Min Act: -0.0001
Data Index: 524700 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.7409. Min Act: -0.0001
Data Index: 5871 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3236. Min Range: -1.3236
Max Act: 0.8033. Min Act: -0.0001
Data Index: 846429 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19