Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6087 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.1129. Min Range: -4.1129
Max Act: 4.1129. Min Act: -0.0001
Data Index: 170547 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.8767. Min Act: -0.0001
Data Index: 92410 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.7802. Min Act: -0.0001
Data Index: 599353 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1129. Min Range: -4.1129
Max Act: 4.0277. Min Act: -0.0001
Data Index: 685357 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.5143. Min Act: -0.0001
Data Index: 355048 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.1365. Min Act: -0.0001
Data Index: 148165 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.3058. Min Act: -0.0001
Data Index: 100658 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.5381. Min Act: -0.0001
Data Index: 175732 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1129. Min Range: -4.1129
Max Act: 2.9981. Min Act: -0.0001
Data Index: 765980 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.0761. Min Act: -0.0001
Data Index: 126438 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.0200. Min Act: -0.0001
Data Index: 561162 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1129. Min Range: -4.1129
Max Act: 2.9647. Min Act: -0.0001
Data Index: 1054871 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.0595. Min Act: -0.0001
Data Index: 1317585 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.2196. Min Act: -0.0001
Data Index: 949828 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1129. Min Range: -4.1129
Max Act: 3.1932. Min Act: -0.0001
Data Index: 90568 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1129. Min Range: -4.1129
Max Act: 2.8811. Min Act: -0.0001
Data Index: 481622 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1129. Min Range: -4.1129
Max Act: 2.8902. Min Act: -0.0001
Data Index: 1108517 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1129. Min Range: -4.1129
Max Act: 2.5031. Min Act: -0.0001
Data Index: 1140073 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1129. Min Range: -4.1129
Max Act: 2.6567. Min Act: -0.0001
Data Index: 831433 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1129. Min Range: -4.1129
Max Act: 2.7077. Min Act: -0.0001
Data Index: 103076 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19