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

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

Neuron 2498 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: 0.3041. Min Range: -0.3041

Max Act: 0.3041. Min Act: -0.0000

Data Index: 720386 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2979. Min Act: -0.0001

Data Index: 683201 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2795. Min Act: -0.0001

Data Index: 379415 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2560. Min Act: -0.0000

Data Index: 971494 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2601. Min Act: -0.0001

Data Index: 955890 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2436. Min Act: -0.0001

Data Index: 240873 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2429. Min Act: -0.0001

Data Index: 1213407 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2503. Min Act: -0.0001

Data Index: 207988 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2428. Min Act: -0.0001

Data Index: 1358531 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2469. Min Act: -0.0001

Data Index: 578369 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2554. Min Act: -0.0000

Data Index: 301630 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2392. Min Act: -0.0001

Data Index: 1337138 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2454. Min Act: -0.0001

Data Index: 1107159 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2451. Min Act: -0.0001

Data Index: 1170514 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2354. Min Act: -0.0001

Data Index: 429091 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2419. Min Act: -0.0001

Data Index: 1311534 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2365. Min Act: -0.0001

Data Index: 1074570 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2432. Min Act: -0.0001

Data Index: 136025 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2350. Min Act: -0.0001

Data Index: 317297 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2504. Min Act: -0.0001

Data Index: 1026742 (C4 (Web Text))

Max Activating Token Index: 649