Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3156 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.8890. Min Act: -0.0001
Data Index: 732091 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.9994. Min Act: -0.0001
Data Index: 631204 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.5508. Min Act: -0.0001
Data Index: 329431 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.5283. Min Act: -0.0000
Data Index: 445511 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.4965. Min Act: -0.0001
Data Index: 867219 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.2427. Min Act: -0.0001
Data Index: 281462 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.3362. Min Act: -0.0001
Data Index: 770430 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.3122. Min Act: -0.0001
Data Index: 759677 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.2968. Min Act: -0.0000
Data Index: 21131 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.2863. Min Act: -0.0000
Data Index: 465933 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.4774. Min Act: -0.0000
Data Index: 203850 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9994. Min Range: -2.9994
Max Act: 1.9977. Min Act: -0.0000
Data Index: 306367 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9994. Min Range: -2.9994
Max Act: 1.9677. Min Act: -0.0001
Data Index: 308326 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.0466. Min Act: -0.0001
Data Index: 570930 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9994. Min Range: -2.9994
Max Act: 1.8559. Min Act: -0.0000
Data Index: 27211 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9994. Min Range: -2.9994
Max Act: 1.9320. Min Act: -0.0000
Data Index: 1041236 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.1423. Min Act: -0.0001
Data Index: 947554 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.0105. Min Act: -0.0001
Data Index: 1113360 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.1048. Min Act: -0.0000
Data Index: 691990 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9994. Min Range: -2.9994
Max Act: 2.0745. Min Act: -0.0000
Data Index: 1038604 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19