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

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

Neuron 4138 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5305. Min Range: -2.5305

Max Act: 2.5305. Min Act: -0.0000

Data Index: 221393 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 2.5305. Min Range: -2.5305

Max Act: 2.2674. Min Act: -0.0000

Data Index: 522684 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 2.5305. Min Range: -2.5305

Max Act: 2.0944. Min Act: -0.0000

Data Index: 1283850 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.9232. Min Act: -0.0000

Data Index: 98696 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.8120. Min Act: -0.0000

Data Index: 256282 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.7008. Min Act: -0.0000

Data Index: 1353780 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.7778. Min Act: -0.0000

Data Index: 746923 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.8705. Min Act: -0.0000

Data Index: 361532 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.5815. Min Act: 0.0000

Data Index: 892165 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.5733. Min Act: -0.0000

Data Index: 448997 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.7331. Min Act: -0.0000

Data Index: 1287310 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.5369. Min Act: -0.0000

Data Index: 467265 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.4639. Min Act: -0.0000

Data Index: 729747 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.4958. Min Act: -0.0000

Data Index: 729050 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.6634. Min Act: -0.0000

Data Index: 334178 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.6634. Min Act: -0.0000

Data Index: 1267723 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.3383. Min Act: -0.0000

Data Index: 223277 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1316111 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.4626. Min Act: -0.0000

Data Index: 260155 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 2.5305. Min Range: -2.5305

Max Act: 1.2612. Min Act: -0.0000

Data Index: 921750 (C4 (Web Text))

Max Activating Token Index: 195