Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4707 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5679. Min Act: -0.0001

Data Index: 466253 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5349. Min Act: -0.0001

Data Index: 1492413 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5498. Min Act: -0.0001

Data Index: 1610786 (Python Code)

Max Activating Token Index: 932

Text #3

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5202. Min Act: -0.0001

Data Index: 1553178 (Python Code)

Max Activating Token Index: 964

Text #4

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5176. Min Act: -0.0001

Data Index: 1536924 (Python Code)

Max Activating Token Index: 792

Text #5

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5081. Min Act: -0.0001

Data Index: 1383539 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5143. Min Act: -0.0001

Data Index: 724459 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5063. Min Act: -0.0001

Data Index: 1533360 (Python Code)

Max Activating Token Index: 880

Text #8

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5253. Min Act: -0.0001

Data Index: 388761 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5034. Min Act: -0.0001

Data Index: 1629701 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4999. Min Act: -0.0001

Data Index: 1532847 (Python Code)

Max Activating Token Index: 778

Text #11

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4982. Min Act: -0.0001

Data Index: 1591120 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4916. Min Act: -0.0001

Data Index: 1443871 (Python Code)

Max Activating Token Index: 324

Text #13

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4763. Min Act: -0.0001

Data Index: 1451760 (Python Code)

Max Activating Token Index: 229

Text #14

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5089. Min Act: -0.0001

Data Index: 1463639 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4803. Min Act: -0.0001

Data Index: 399897 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4759. Min Act: -0.0001

Data Index: 1582509 (Python Code)

Max Activating Token Index: 854

Text #17

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4709. Min Act: -0.0001

Data Index: 1612320 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5031. Min Act: -0.0001

Data Index: 1655218 (Python Code)

Max Activating Token Index: 618

Text #19

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4397. Min Act: -0.0001

Data Index: 274046 (C4 (Web Text))

Max Activating Token Index: 267