Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1067 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1456. Min Act: -0.0001
Data Index: 475780 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1073. Min Act: -0.0001
Data Index: 486274 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1301. Min Act: -0.0001
Data Index: 553704 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1157. Min Act: -0.0001
Data Index: 700708 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1097. Min Act: -0.0001
Data Index: 29492 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1068. Min Act: -0.0001
Data Index: 158549 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1098. Min Act: -0.0001
Data Index: 757884 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1086. Min Act: -0.0001
Data Index: 590031 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1260. Min Act: -0.0001
Data Index: 131638 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1013. Min Act: -0.0001
Data Index: 580228 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1027. Min Act: -0.0001
Data Index: 1037926 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.0857. Min Act: -0.0001
Data Index: 576877 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.0959. Min Act: -0.0001
Data Index: 514037 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.0952. Min Act: -0.0001
Data Index: 1607583 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.0921. Min Act: -0.0001
Data Index: 1218567 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.0942. Min Act: -0.0001
Data Index: 1322601 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1012. Min Act: -0.0001
Data Index: 255271 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.0946. Min Act: -0.0001
Data Index: 1383399 (Python Code)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.1207. Min Act: -0.0001
Data Index: 711349 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1456. Min Range: -0.1456
Max Act: 0.0948. Min Act: -0.0001
Data Index: 308333 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19