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

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

Neuron 3680 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: 0.3465. Min Range: -0.3465

Max Act: 0.3465. Min Act: -0.0001

Data Index: 577684 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3280. Min Act: -0.0001

Data Index: 521527 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3334. Min Act: -0.0001

Data Index: 106425 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3264. Min Act: -0.0000

Data Index: 95373 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3160. Min Act: -0.0001

Data Index: 686533 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3042. Min Act: -0.0001

Data Index: 971173 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1341670 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.3034. Min Act: -0.0001

Data Index: 491859 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2961. Min Act: -0.0001

Data Index: 51061 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2662. Min Act: -0.0001

Data Index: 1112890 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2867. Min Act: -0.0001

Data Index: 781033 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2876. Min Act: -0.0001

Data Index: 1177381 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2785. Min Act: -0.0001

Data Index: 212523 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2555. Min Act: -0.0000

Data Index: 98191 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2614. Min Act: -0.0001

Data Index: 702181 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2660. Min Act: -0.0001

Data Index: 231956 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2592. Min Act: -0.0000

Data Index: 350941 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2359. Min Act: -0.0000

Data Index: 538333 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2497. Min Act: -0.0001

Data Index: 244758 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.3465. Min Range: -0.3465

Max Act: 0.2369. Min Act: -0.0001

Data Index: 922476 (C4 (Web Text))

Max Activating Token Index: 438