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

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

Neuron 1107 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.4108. Min Act: -0.1700

Data Index: 639362 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.3324. Min Act: -0.1700

Data Index: 1306630 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.3167. Min Act: -0.1700

Data Index: 762215 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.2224. Min Act: -0.1700

Data Index: 1300320 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.2067. Min Act: -0.1700

Data Index: 601877 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.2224. Min Act: -0.1700

Data Index: 169642 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.2224. Min Act: -0.1700

Data Index: 1314944 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.2067. Min Act: -0.1700

Data Index: 1338875 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1595. Min Act: -0.1700

Data Index: 710426 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1595. Min Act: -0.1700

Data Index: 159257 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1595. Min Act: -0.1700

Data Index: 230921 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1910. Min Act: -0.1700

Data Index: 161454 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1752. Min Act: -0.1700

Data Index: 357221 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1437. Min Act: -0.1700

Data Index: 842840 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.2067. Min Act: -0.1700

Data Index: 1236618 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1437. Min Act: -0.1700

Data Index: 659534 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1595. Min Act: -0.1700

Data Index: 1023567 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1280. Min Act: -0.1700

Data Index: 408080 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1122. Min Act: -0.1700

Data Index: 1183283 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 3.4108. Min Range: -3.4108

Max Act: 3.1437. Min Act: -0.1700

Data Index: 31088 (C4 (Web Text))

Max Activating Token Index: 958