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

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

Neuron 3615 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.3157. Min Act: -0.0000

Data Index: 1280071 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.2682. Min Act: -0.0000

Data Index: 471240 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.2612. Min Act: -0.0001

Data Index: 812901 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.2483. Min Act: -0.0000

Data Index: 1122476 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.2088. Min Act: -0.0001

Data Index: 819063 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.1804. Min Act: -0.0001

Data Index: 1236671 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.1719. Min Act: -0.0001

Data Index: 1177187 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.1653. Min Act: -0.0001

Data Index: 1195380 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.1373. Min Act: -0.0000

Data Index: 756249 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.1355. Min Act: -0.0000

Data Index: 867642 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1006667 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.1157. Min Act: -0.0001

Data Index: 1276377 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.0967. Min Act: -0.0001

Data Index: 765642 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.0872. Min Act: -0.0001

Data Index: 1345758 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1316433 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.0693. Min Act: -0.0001

Data Index: 946425 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.0656. Min Act: -0.0001

Data Index: 1100449 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.0585. Min Act: -0.0001

Data Index: 26512 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.0625. Min Act: -0.0001

Data Index: 467947 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 1.3157. Min Range: -1.3157

Max Act: 1.0331. Min Act: -0.0001

Data Index: 831610 (C4 (Web Text))

Max Activating Token Index: 337