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

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

Neuron 607 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1943. Min Range: -1.1943

Max Act: 1.1943. Min Act: -0.0001

Data Index: 118355 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.9757. Min Act: -0.0001

Data Index: 1129408 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.9049. Min Act: -0.0001

Data Index: 173618 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8633. Min Act: -0.0001

Data Index: 9369 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7938. Min Act: -0.0001

Data Index: 239024 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8418. Min Act: -0.0001

Data Index: 947224 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8659. Min Act: -0.0001

Data Index: 501532 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8544. Min Act: -0.0001

Data Index: 883091 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8035. Min Act: -0.0001

Data Index: 1267738 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7969. Min Act: -0.0001

Data Index: 330225 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7032. Min Act: -0.0001

Data Index: 345132 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7729. Min Act: -0.0001

Data Index: 31051 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7432. Min Act: -0.0001

Data Index: 151534 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7607. Min Act: -0.0001

Data Index: 1318625 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7234. Min Act: -0.0001

Data Index: 1226577 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.8579. Min Act: -0.0001

Data Index: 1021115 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7323. Min Act: -0.0001

Data Index: 366248 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7784. Min Act: -0.0001

Data Index: 570286 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7687. Min Act: -0.0001

Data Index: 816039 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.1943. Min Range: -1.1943

Max Act: 0.7959. Min Act: -0.0001

Data Index: 1166940 (C4 (Web Text))

Max Activating Token Index: 830