Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1883 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.4359. Min Act: -0.1700

Data Index: 1354651 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3104. Min Act: -0.1700

Data Index: 411149 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3418. Min Act: -0.1700

Data Index: 677228 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.3261. Min Act: -0.1700

Data Index: 102165 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.2947. Min Act: -0.1700

Data Index: 640160 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.2318. Min Act: -0.1700

Data Index: 1324403 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.2318. Min Act: -0.1700

Data Index: 1075394 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.2161. Min Act: -0.1700

Data Index: 1141000 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.2003. Min Act: -0.1700

Data Index: 755799 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1689. Min Act: -0.1700

Data Index: 117873 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1846. Min Act: -0.1700

Data Index: 235367 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1846. Min Act: -0.1700

Data Index: 196997 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1846. Min Act: -0.1700

Data Index: 496043 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1846. Min Act: -0.1700

Data Index: 420495 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1531. Min Act: -0.1700

Data Index: 1191451 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1689. Min Act: -0.1700

Data Index: 1046897 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1689. Min Act: -0.1700

Data Index: 1111953 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1846. Min Act: -0.1700

Data Index: 80068 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1689. Min Act: -0.1700

Data Index: 1086433 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 3.4359. Min Range: -3.4359

Max Act: 3.1846. Min Act: -0.1700

Data Index: 600447 (C4 (Web Text))

Max Activating Token Index: 615