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

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

Neuron 670 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1936. Min Range: -1.1936

Max Act: 1.1936. Min Act: -0.0000

Data Index: 10501 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1298102 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.9203. Min Act: -0.0000

Data Index: 19959 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8885. Min Act: -0.0000

Data Index: 617320 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8265. Min Act: -0.0000

Data Index: 217243 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1369238 (Python Code)

Max Activating Token Index: 257

Text #6

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.7458. Min Act: -0.0000

Data Index: 142475 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.8318. Min Act: -0.0000

Data Index: 439042 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.6992. Min Act: -0.0000

Data Index: 309290 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.7957. Min Act: -0.0000

Data Index: 662485 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.6382. Min Act: -0.0000

Data Index: 505914 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.7985. Min Act: -0.0000

Data Index: 435578 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1132989 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1033197 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.6327. Min Act: -0.0000

Data Index: 347987 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1429073 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.6563. Min Act: -0.0000

Data Index: 631749 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.6237. Min Act: -0.0000

Data Index: 144832 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.6320. Min Act: -0.0000

Data Index: 392487 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 1.1936. Min Range: -1.1936

Max Act: 0.6336. Min Act: -0.0000

Data Index: 673181 (C4 (Web Text))

Max Activating Token Index: 402