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

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

Neuron 1767 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1301. Min Range: -3.1301

Max Act: 3.1190. Min Act: -0.0001

Data Index: 477515 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 3.1301. Min Range: -3.1301

Max Act: 3.1301. Min Act: -0.0001

Data Index: 654316 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.8566. Min Act: -0.0001

Data Index: 93292 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.6485. Min Act: -0.0001

Data Index: 517635 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.6432. Min Act: -0.0001

Data Index: 205772 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.5912. Min Act: -0.0001

Data Index: 1310174 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.7221. Min Act: -0.0001

Data Index: 880841 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.4511. Min Act: -0.0001

Data Index: 1305218 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.4513. Min Act: -0.0001

Data Index: 1222948 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.5890. Min Act: -0.0001

Data Index: 1085239 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.6822. Min Act: -0.0001

Data Index: 728040 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.5196. Min Act: -0.0001

Data Index: 693223 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.5077. Min Act: -0.0001

Data Index: 626909 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.5038. Min Act: -0.0001

Data Index: 142986 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.4919. Min Act: -0.0001

Data Index: 1107945 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.4839. Min Act: -0.0001

Data Index: 999236 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.4330. Min Act: -0.0001

Data Index: 71114 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.4277. Min Act: -0.0001

Data Index: 15481 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.4201. Min Act: -0.0001

Data Index: 880683 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 3.1301. Min Range: -3.1301

Max Act: 2.2937. Min Act: -0.0001

Data Index: 1286104 (C4 (Web Text))

Max Activating Token Index: 632