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

Dataset: The Pile

Neuron 1334 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.2101. Min Act: -0.0000

Data Index: 741855 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.1310. Min Act: -0.0000

Data Index: 341673 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0467. Min Act: -0.0000

Data Index: 931337 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1346182 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1356117 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1086285 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1240038 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0912. Min Act: -0.0000

Data Index: 269908 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1423612 (The Pile)

Max Activating Token Index: 232

Text #9

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1581030 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9990. Min Act: -0.0000

Data Index: 214577 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1267710 (The Pile)

Max Activating Token Index: 417

Text #12

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0469. Min Act: -0.0000

Data Index: 903202 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1640056 (The Pile)

Max Activating Token Index: 184

Text #14

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1585500 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0592. Min Act: -0.0000

Data Index: 580600 (The Pile)

Max Activating Token Index: 878

Text #16

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9996. Min Act: -0.0000

Data Index: 485001 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9267. Min Act: -0.0000

Data Index: 940876 (The Pile)

Max Activating Token Index: 899

Text #18

Max Range: 1.2101. Min Range: -1.2101

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1499043 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 1.2101. Min Range: -1.2101

Max Act: 0.9946. Min Act: -0.0000

Data Index: 696961 (The Pile)

Max Activating Token Index: 805