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

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

Neuron 4067 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.3107. Min Act: -0.0000

Data Index: 946161 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2595. Min Act: -0.0001

Data Index: 1389762 (Python Code)

Max Activating Token Index: 392

Text #2

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2544. Min Act: -0.0001

Data Index: 167124 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2392. Min Act: -0.0000

Data Index: 968733 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2372. Min Act: -0.0001

Data Index: 82546 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2347. Min Act: -0.0000

Data Index: 288890 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2631. Min Act: -0.0001

Data Index: 1529260 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1357987 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2312. Min Act: -0.0001

Data Index: 21837 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2216. Min Act: -0.0000

Data Index: 915081 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2326. Min Act: -0.0001

Data Index: 580669 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2348. Min Act: -0.0000

Data Index: 703684 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1236664 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2328. Min Act: -0.0000

Data Index: 463005 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2216. Min Act: -0.0000

Data Index: 851930 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1351816 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2209. Min Act: -0.0000

Data Index: 40036 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2185. Min Act: -0.0000

Data Index: 240052 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2164. Min Act: -0.0001

Data Index: 527130 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.3107. Min Range: -0.3107

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1343107 (C4 (Web Text))

Max Activating Token Index: 475