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

Dataset: The Pile

Neuron 3650 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: 0.3458. Min Range: -0.3458

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1893075 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3411. Min Act: -0.0000

Data Index: 830736 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3367. Min Act: -0.0000

Data Index: 686540 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3458. Min Act: -0.0000

Data Index: 731088 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1073145 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1019368 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3241. Min Act: -0.0000

Data Index: 690592 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1923986 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3187. Min Act: -0.0000

Data Index: 192324 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3129. Min Act: -0.0000

Data Index: 836948 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3038. Min Act: -0.0000

Data Index: 961044 (The Pile)

Max Activating Token Index: 876

Text #11

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1603010 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.3008. Min Act: -0.0000

Data Index: 988742 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1583580 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2990. Min Act: -0.0000

Data Index: 447643 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1768361 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2886. Min Act: -0.0000

Data Index: 521303 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2955. Min Act: -0.0000

Data Index: 657293 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2847. Min Act: -0.0000

Data Index: 335338 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 0.3458. Min Range: -0.3458

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1047517 (The Pile)

Max Activating Token Index: 820