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

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

Neuron 1325 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: 0.5164. Min Range: -0.5164

Max Act: 0.5164. Min Act: -0.0001

Data Index: 766985 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4993. Min Act: -0.0001

Data Index: 718559 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4363. Min Act: -0.0001

Data Index: 486077 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4561. Min Act: -0.0001

Data Index: 746446 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4187. Min Act: -0.0001

Data Index: 496027 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.4362. Min Act: -0.0001

Data Index: 979077 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3624. Min Act: -0.0001

Data Index: 1102573 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3827. Min Act: -0.0001

Data Index: 437111 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3599. Min Act: -0.0001

Data Index: 322306 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3709. Min Act: -0.0001

Data Index: 167048 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3632. Min Act: -0.0001

Data Index: 789844 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3521. Min Act: -0.0001

Data Index: 654494 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3381. Min Act: -0.0001

Data Index: 1068354 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3382. Min Act: -0.0001

Data Index: 797576 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3356. Min Act: -0.0001

Data Index: 893392 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3606. Min Act: -0.0001

Data Index: 207673 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3445. Min Act: -0.0001

Data Index: 535926 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3432. Min Act: -0.0001

Data Index: 937278 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3393. Min Act: -0.0001

Data Index: 731916 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.5164. Min Range: -0.5164

Max Act: 0.3537. Min Act: -0.0001

Data Index: 1014100 (C4 (Web Text))

Max Activating Token Index: 901