Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2481 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3933. Min Act: -0.0000

Data Index: 420444 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.3881. Min Act: -0.0000

Data Index: 286823 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2943. Min Act: -0.0000

Data Index: 124831 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2489. Min Act: -0.0001

Data Index: 1136010 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1258206 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2468. Min Act: -0.0000

Data Index: 315348 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2474. Min Act: -0.0000

Data Index: 410834 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2626. Min Act: -0.0000

Data Index: 951076 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2579. Min Act: -0.0000

Data Index: 410626 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1020226 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1070245 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2311. Min Act: -0.0000

Data Index: 328535 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2334. Min Act: -0.0000

Data Index: 930788 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2341. Min Act: -0.0000

Data Index: 131299 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2161. Min Act: -0.0000

Data Index: 546744 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2338. Min Act: -0.0000

Data Index: 214155 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2165. Min Act: -0.0000

Data Index: 440945 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1118328 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2267. Min Act: -0.0000

Data Index: 1012029 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.3933. Min Range: -0.3933

Max Act: 0.2347. Min Act: -0.0000

Data Index: 630914 (C4 (Web Text))

Max Activating Token Index: 99