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

Dataset: The Pile

Neuron 3736 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1453381 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5523. Min Act: -0.0000

Data Index: 442983 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1332212 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5541. Min Act: -0.0000

Data Index: 769012 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1993458 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4987. Min Act: 0.0000

Data Index: 208498 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4585. Min Act: -0.0000

Data Index: 909554 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4982. Min Act: 0.0000

Data Index: 1151919 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4548. Min Act: -0.0000

Data Index: 108214 (The Pile)

Max Activating Token Index: 713

Text #9

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1550728 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1292478 (The Pile)

Max Activating Token Index: 369

Text #11

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1833443 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4344. Min Act: -0.0000

Data Index: 482300 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1256230 (The Pile)

Max Activating Token Index: 813

Text #14

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4309. Min Act: -0.0001

Data Index: 1403752 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4531. Min Act: 0.0000

Data Index: 396575 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1294567 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1842852 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1544127 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 0.6154. Min Range: -0.6154

Max Act: 0.4489. Min Act: -0.0000

Data Index: 621253 (The Pile)

Max Activating Token Index: 118