Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2496 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.4125. Min Act: -0.0000

Data Index: 657928 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3714. Min Act: -0.0000

Data Index: 256698 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1179403 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3288. Min Act: -0.0000

Data Index: 128481 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1042600 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3236. Min Act: 0.0000

Data Index: 594749 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3137. Min Act: -0.0000

Data Index: 16228 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3251. Min Act: 0.0000

Data Index: 838739 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3070. Min Act: 0.0001

Data Index: 133938 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3028. Min Act: -0.0000

Data Index: 412079 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3133. Min Act: 0.0001

Data Index: 238627 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3134. Min Act: 0.0000

Data Index: 138502 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1342511 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.2947. Min Act: -0.0000

Data Index: 727255 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.3021. Min Act: -0.0000

Data Index: 189054 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.2993. Min Act: -0.0000

Data Index: 161054 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.2882. Min Act: -0.0000

Data Index: 272126 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.2789. Min Act: -0.0000

Data Index: 786232 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1129242 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.4125. Min Range: -0.4125

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1197343 (C4 (Web Text))

Max Activating Token Index: 639