Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2904 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.4925. Min Act: -0.0000

Data Index: 58244 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1655. Min Act: -0.0000

Data Index: 307104 (The Pile)

Max Activating Token Index: 929

Text #2

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2882. Min Act: -0.0000

Data Index: 954109 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2486. Min Act: -0.0000

Data Index: 884684 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1939053 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1875671 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1757376 (The Pile)

Max Activating Token Index: 126

Text #7

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1920. Min Act: -0.0000

Data Index: 1576359 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1970. Min Act: -0.0000

Data Index: 665695 (The Pile)

Max Activating Token Index: 525

Text #9

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1345. Min Act: -0.0000

Data Index: 584701 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1197657 (The Pile)

Max Activating Token Index: 820

Text #11

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1095. Min Act: -0.0000

Data Index: 561901 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2458. Min Act: -0.0000

Data Index: 149494 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 1.4925. Min Range: -1.4925

Max Act: 0.9975. Min Act: -0.0000

Data Index: 762070 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1631992 (The Pile)

Max Activating Token Index: 423

Text #15

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1309048 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1641. Min Act: -0.0000

Data Index: 737092 (The Pile)

Max Activating Token Index: 280

Text #17

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1405. Min Act: -0.0000

Data Index: 1518069 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1474. Min Act: -0.0000

Data Index: 1816412 (The Pile)

Max Activating Token Index: 685

Text #19

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1082. Min Act: -0.0000

Data Index: 63989 (The Pile)

Max Activating Token Index: 692