Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1009 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.3036. Min Act: -0.0000

Data Index: 28278 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2800. Min Act: -0.0001

Data Index: 15045 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2744. Min Act: -0.0000

Data Index: 973822 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2564. Min Act: -0.0001

Data Index: 657136 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2464. Min Act: -0.0000

Data Index: 111098 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2529. Min Act: -0.0000

Data Index: 182788 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2296. Min Act: 0.0001

Data Index: 1179704 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2283. Min Act: -0.0001

Data Index: 694824 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2270. Min Act: -0.0000

Data Index: 753684 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2259. Min Act: -0.0000

Data Index: 901651 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2298. Min Act: -0.0001

Data Index: 355988 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2166. Min Act: -0.0001

Data Index: 1080689 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1172663 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2206. Min Act: -0.0000

Data Index: 483571 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2196. Min Act: -0.0001

Data Index: 624514 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2217. Min Act: -0.0000

Data Index: 134933 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2159. Min Act: -0.0001

Data Index: 1352940 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2167. Min Act: -0.0001

Data Index: 1238302 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2092. Min Act: -0.0001

Data Index: 292903 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2138. Min Act: -0.0001

Data Index: 1306982 (C4 (Web Text))

Max Activating Token Index: 134