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

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

Neuron 2627 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: 3.4951. Min Range: -3.4951

Max Act: 3.2168. Min Act: -0.0001

Data Index: 663360 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.3620. Min Act: -0.0001

Data Index: 1303831 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.2043. Min Act: -0.0001

Data Index: 375488 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.4951. Min Act: -0.0001

Data Index: 521291 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.3354. Min Act: -0.0001

Data Index: 348431 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.2973. Min Act: -0.0001

Data Index: 457628 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.1070. Min Act: -0.0001

Data Index: 1116167 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.0825. Min Act: -0.0001

Data Index: 406228 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.3811. Min Act: -0.0001

Data Index: 444215 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.0239. Min Act: -0.0001

Data Index: 498348 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 3.4951. Min Range: -3.4951

Max Act: 2.7548. Min Act: -0.0001

Data Index: 242956 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.0257. Min Act: -0.0001

Data Index: 1333749 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.0479. Min Act: -0.0001

Data Index: 225522 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.0014. Min Act: -0.0001

Data Index: 498711 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.1235. Min Act: -0.0001

Data Index: 826757 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 3.4951. Min Range: -3.4951

Max Act: 2.9892. Min Act: -0.0001

Data Index: 573913 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.1074. Min Act: -0.0001

Data Index: 1210262 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.2157. Min Act: -0.0001

Data Index: 1084831 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 3.4951. Min Range: -3.4951

Max Act: 3.2054. Min Act: -0.0001

Data Index: 1231398 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 3.4951. Min Range: -3.4951

Max Act: 2.9330. Min Act: -0.0001

Data Index: 788156 (C4 (Web Text))

Max Activating Token Index: 11