Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2366 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.6516. Min Act: -0.0001
Data Index: 321083 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.7699. Min Act: -0.0001
Data Index: 1186405 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.5553. Min Act: -0.0001
Data Index: 1014762 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.4379. Min Act: -0.0001
Data Index: 426273 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.4261. Min Act: -0.0001
Data Index: 772210 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.4533. Min Act: -0.0001
Data Index: 867176 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.4760. Min Act: -0.0001
Data Index: 632961 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.4009. Min Act: -0.0001
Data Index: 1176664 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.4619. Min Act: -0.0001
Data Index: 1005785 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.4287. Min Act: -0.0001
Data Index: 1286015 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.2776. Min Act: -0.0001
Data Index: 433328 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.3422. Min Act: -0.0001
Data Index: 867797 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.2263. Min Act: -0.0001
Data Index: 79438 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.3178. Min Act: -0.0001
Data Index: 176749 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.3022. Min Act: -0.0001
Data Index: 1073069 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.2403. Min Act: -0.0001
Data Index: 1123855 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.2236. Min Act: -0.0001
Data Index: 123625 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.2759. Min Act: -0.0001
Data Index: 100753 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.2295. Min Act: -0.0001
Data Index: 87884 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7699. Min Range: -1.7699
Max Act: 1.1876. Min Act: -0.0001
Data Index: 141847 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19