Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1261 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0448. Min Range: -2.0448
Max Act: 2.0448. Min Act: -0.0002
Data Index: 396026 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 2.0448. Min Range: -2.0448
Max Act: 1.1819. Min Act: -0.0002
Data Index: 497496 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 2.0448. Min Range: -2.0448
Max Act: 1.0713. Min Act: -0.0002
Data Index: 972130 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 2.0448. Min Range: -2.0448
Max Act: 1.1220. Min Act: -0.0002
Data Index: 1098017 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 2.0448. Min Range: -2.0448
Max Act: 1.0618. Min Act: -0.0002
Data Index: 286823 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 2.0448. Min Range: -2.0448
Max Act: 1.0917. Min Act: -0.0002
Data Index: 1277628 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 2.0448. Min Range: -2.0448
Max Act: 1.1970. Min Act: -0.0002
Data Index: 1014503 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 2.0448. Min Range: -2.0448
Max Act: 1.0656. Min Act: -0.0002
Data Index: 1047667 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 2.0448. Min Range: -2.0448
Max Act: 1.0282. Min Act: -0.0002
Data Index: 727552 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.9328. Min Act: -0.0002
Data Index: 1400058 (Python Code)
Max Activating Token Index: 377
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.8683. Min Act: -0.0002
Data Index: 1518067 (Python Code)
Max Activating Token Index: 886
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.8113. Min Act: -0.0002
Data Index: 896256 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.6857. Min Act: -0.0002
Data Index: 102980 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.8839. Min Act: -0.0002
Data Index: 151087 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.8171. Min Act: -0.0002
Data Index: 988837 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.7643. Min Act: -0.0002
Data Index: 1300141 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.8322. Min Act: -0.0002
Data Index: 1605750 (Python Code)
Max Activating Token Index: 700
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.7280. Min Act: -0.0002
Data Index: 235594 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.7738. Min Act: -0.0002
Data Index: 669616 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 2.0448. Min Range: -2.0448
Max Act: 0.7752. Min Act: -0.0002
Data Index: 1002817 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full textTruncated
Full Text #19