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

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

Neuron 4470 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.9105. Min Act: -0.0001

Data Index: 546536 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7167. Min Act: -0.0001

Data Index: 1499646 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.6883. Min Act: -0.0001

Data Index: 1513438 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.5191. Min Act: -0.0001

Data Index: 633802 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.6313. Min Act: -0.0001

Data Index: 1432496 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4886. Min Act: -0.0001

Data Index: 1420564 (Python Code)

Max Activating Token Index: 994

Text #6

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4675. Min Act: -0.0001

Data Index: 1645256 (Python Code)

Max Activating Token Index: 519

Text #7

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4574. Min Act: -0.0001

Data Index: 1067675 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4987. Min Act: -0.0001

Data Index: 1569931 (Python Code)

Max Activating Token Index: 823

Text #9

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4324. Min Act: -0.0001

Data Index: 1647306 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.4049. Min Act: -0.0001

Data Index: 1605220 (Python Code)

Max Activating Token Index: 55

Text #11

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.2742. Min Act: -0.0001

Data Index: 1445372 (Python Code)

Max Activating Token Index: 214

Text #12

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.2210. Min Act: -0.0001

Data Index: 1554723 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.3154. Min Act: -0.0001

Data Index: 1564275 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.3205. Min Act: -0.0001

Data Index: 339305 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.3967. Min Act: -0.0001

Data Index: 1286600 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.2965. Min Act: -0.0001

Data Index: 1360781 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.2920. Min Act: -0.0001

Data Index: 1244869 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.2190. Min Act: -0.0001

Data Index: 1361467 (Python Code)

Max Activating Token Index: 488

Text #19

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.2859. Min Act: -0.0001

Data Index: 1417849 (Python Code)

Max Activating Token Index: 521