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

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

Neuron 150 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0705. Min Range: -1.0705

Max Act: 1.0705. Min Act: -0.0001

Data Index: 845783 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.8583. Min Act: -0.0001

Data Index: 1143975 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6784. Min Act: -0.0001

Data Index: 799697 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7276. Min Act: -0.0001

Data Index: 756053 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6423. Min Act: -0.0001

Data Index: 754600 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6578. Min Act: -0.0001

Data Index: 384772 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6084. Min Act: -0.0001

Data Index: 662381 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6590. Min Act: -0.0001

Data Index: 281524 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6132. Min Act: -0.0001

Data Index: 933255 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.7158. Min Act: -0.0001

Data Index: 1305088 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6505. Min Act: -0.0001

Data Index: 562391 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6263. Min Act: -0.0001

Data Index: 845213 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.5823. Min Act: -0.0001

Data Index: 540999 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.4942. Min Act: -0.0001

Data Index: 621692 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.5756. Min Act: -0.0001

Data Index: 495347 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6545. Min Act: -0.0001

Data Index: 1012091 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6326. Min Act: -0.0001

Data Index: 231670 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.6367. Min Act: -0.0001

Data Index: 175431 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.5897. Min Act: -0.0001

Data Index: 368607 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 1.0705. Min Range: -1.0705

Max Act: 0.5998. Min Act: -0.0001

Data Index: 1357661 (C4 (Web Text))

Max Activating Token Index: 578