Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1618 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1933. Min Act: -0.0001

Data Index: 715562 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1935. Min Act: -0.0001

Data Index: 741087 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1662. Min Act: -0.0001

Data Index: 1203240 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1594. Min Act: -0.0001

Data Index: 834185 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1671. Min Act: -0.0001

Data Index: 1276054 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1723. Min Act: -0.0001

Data Index: 1126220 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1441. Min Act: -0.0001

Data Index: 674136 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1533. Min Act: -0.0001

Data Index: 284258 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1538. Min Act: -0.0001

Data Index: 828486 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1312140 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1485. Min Act: -0.0001

Data Index: 741210 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1237410 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1144702 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1445. Min Act: -0.0001

Data Index: 126542 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1103625 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1319445 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1187336 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1471. Min Act: -0.0001

Data Index: 560110 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1169119 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1411. Min Act: -0.0001

Data Index: 595037 (C4 (Web Text))

Max Activating Token Index: 948