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

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

Neuron 3895 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0492. Min Range: -1.0492

Max Act: 1.0492. Min Act: -0.0000

Data Index: 1366092 (Python Code)

Max Activating Token Index: 544

Text #1

Max Range: 1.0492. Min Range: -1.0492

Max Act: 1.0418. Min Act: -0.0000

Data Index: 1373461 (Python Code)

Max Activating Token Index: 916

Text #2

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1317721 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1495085 (Python Code)

Max Activating Token Index: 453

Text #4

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1493389 (Python Code)

Max Activating Token Index: 376

Text #5

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1610925 (Python Code)

Max Activating Token Index: 990

Text #6

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1392141 (Python Code)

Max Activating Token Index: 651

Text #7

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1498911 (Python Code)

Max Activating Token Index: 518

Text #8

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1455193 (Python Code)

Max Activating Token Index: 832

Text #9

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1639745 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1369524 (Python Code)

Max Activating Token Index: 369

Text #11

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1428327 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1550343 (Python Code)

Max Activating Token Index: 106

Text #13

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1436211 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1400958 (Python Code)

Max Activating Token Index: 922

Text #15

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1499326 (Python Code)

Max Activating Token Index: 364

Text #16

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1600817 (Python Code)

Max Activating Token Index: 523

Text #17

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1462239 (Python Code)

Max Activating Token Index: 428

Text #18

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1481988 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1456272 (Python Code)

Max Activating Token Index: 767