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

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

Neuron 2848 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: 1.2943. Min Range: -1.2943

Max Act: 1.2943. Min Act: -0.0001

Data Index: 1469991 (Python Code)

Max Activating Token Index: 554

Text #1

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1084. Min Act: -0.0001

Data Index: 1417669 (Python Code)

Max Activating Token Index: 705

Text #2

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1431. Min Act: -0.0001

Data Index: 1394876 (Python Code)

Max Activating Token Index: 53

Text #3

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9851. Min Act: -0.0001

Data Index: 1465196 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9535. Min Act: -0.0001

Data Index: 1603717 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9183. Min Act: -0.0001

Data Index: 1555432 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8673. Min Act: -0.0001

Data Index: 1602885 (Python Code)

Max Activating Token Index: 1019

Text #7

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8172. Min Act: -0.0001

Data Index: 1162397 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.7182. Min Act: -0.0001

Data Index: 1381780 (Python Code)

Max Activating Token Index: 313

Text #9

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.7347. Min Act: -0.0001

Data Index: 1471537 (Python Code)

Max Activating Token Index: 435

Text #10

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.7318. Min Act: -0.0001

Data Index: 1643376 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1622364 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1526840 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.7296. Min Act: -0.0001

Data Index: 1560292 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1507150 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1536365 (Python Code)

Max Activating Token Index: 964

Text #16

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.7158. Min Act: -0.0001

Data Index: 1145613 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.7056. Min Act: -0.0001

Data Index: 1458206 (Python Code)

Max Activating Token Index: 1020

Text #18

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.6620. Min Act: -0.0001

Data Index: 1455436 (Python Code)

Max Activating Token Index: 418

Text #19

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.6184. Min Act: -0.0001

Data Index: 1571549 (Python Code)

Max Activating Token Index: 331