Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2706 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.9732. Min Act: -0.0001
Data Index: 353722 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.8909. Min Act: -0.0001
Data Index: 971969 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.5608. Min Act: -0.0001
Data Index: 1009704 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.6525. Min Act: -0.0001
Data Index: 846115 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.5106. Min Act: -0.0001
Data Index: 896721 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.5748. Min Act: -0.0001
Data Index: 867952 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.5740. Min Act: -0.0001
Data Index: 1116050 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.5669. Min Act: -0.0001
Data Index: 350494 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.4740. Min Act: -0.0001
Data Index: 339616 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.5200. Min Act: -0.0001
Data Index: 631294 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.5727. Min Act: -0.0001
Data Index: 115461 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.3140. Min Act: -0.0001
Data Index: 958316 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.3912. Min Act: -0.0001
Data Index: 977619 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.5263. Min Act: -0.0001
Data Index: 228781 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.4084. Min Act: -0.0001
Data Index: 279142 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.2942. Min Act: -0.0001
Data Index: 632280 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.4074. Min Act: -0.0001
Data Index: 373757 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.3788. Min Act: -0.0001
Data Index: 614778 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.3942. Min Act: -0.0001
Data Index: 1173076 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9732. Min Range: -1.9732
Max Act: 1.3988. Min Act: -0.0001
Data Index: 757972 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19