Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3291 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.6893. Min Range: -2.6893
Max Act: 2.3060. Min Act: -0.0001
Data Index: 15307 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6893. Min Range: -2.6893
Max Act: 2.6893. Min Act: -0.0001
Data Index: 766973 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6893. Min Range: -2.6893
Max Act: 2.2097. Min Act: -0.0001
Data Index: 509673 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6893. Min Range: -2.6893
Max Act: 2.3441. Min Act: -0.0001
Data Index: 539740 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6893. Min Range: -2.6893
Max Act: 2.2745. Min Act: -0.0001
Data Index: 649611 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6893. Min Range: -2.6893
Max Act: 2.0097. Min Act: -0.0001
Data Index: 1241756 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6893. Min Range: -2.6893
Max Act: 2.3056. Min Act: -0.0001
Data Index: 990501 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6893. Min Range: -2.6893
Max Act: 2.0788. Min Act: -0.0001
Data Index: 1072965 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.8392. Min Act: -0.0001
Data Index: 1050954 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6893. Min Range: -2.6893
Max Act: 2.1301. Min Act: -0.0001
Data Index: 390984 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.9334. Min Act: -0.0001
Data Index: 531560 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.9023. Min Act: -0.0001
Data Index: 790445 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.9050. Min Act: -0.0001
Data Index: 1337813 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.8474. Min Act: -0.0001
Data Index: 296046 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.6357. Min Act: -0.0001
Data Index: 928965 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.3364. Min Act: -0.0001
Data Index: 87142 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.8813. Min Act: -0.0001
Data Index: 228939 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.8717. Min Act: -0.0001
Data Index: 1944 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.6402. Min Act: -0.0001
Data Index: 259123 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6893. Min Range: -2.6893
Max Act: 1.2456. Min Act: -0.0001
Data Index: 34124 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19