Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 79 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.5310. Min Act: -0.1700

Data Index: 3609729 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.5123. Min Act: -0.1700

Data Index: 5279253 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.5157. Min Act: -0.1700

Data Index: 5186424 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.5161. Min Act: -0.1700

Data Index: 7003910 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4714. Min Act: -0.1700

Data Index: 6807068 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4800. Min Act: -0.1700

Data Index: 267326 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4934. Min Act: -0.1700

Data Index: 7645092 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4791. Min Act: -0.1700

Data Index: 5361123 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4867. Min Act: -0.1700

Data Index: 211967 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4944. Min Act: -0.1700

Data Index: 4685470 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4961. Min Act: -0.1700

Data Index: 1547695 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4896. Min Act: -0.1700

Data Index: 7750633 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4301. Min Act: -0.1700

Data Index: 4794149 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4576. Min Act: -0.1700

Data Index: 2817100 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4395. Min Act: -0.1700

Data Index: 5162440 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4602. Min Act: -0.1700

Data Index: 2550038 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4502. Min Act: -0.1700

Data Index: 3618675 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4462. Min Act: -0.1700

Data Index: 5956010 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4536. Min Act: -0.1700

Data Index: 7045132 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.5310. Min Range: -4.5310

Max Act: 4.4430. Min Act: -0.1700

Data Index: 5994768 (Open Web Text)

Max Activating Token Index: 5