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

Dataset: Open Web Text

Neuron 538 in Layer 5

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: 4.6532. Min Range: -4.6532

Max Act: 4.6532. Min Act: -0.1700

Data Index: 8511175 (Open Web Text)

Max Activating Token Index: 752

Text #1

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.6172. Min Act: -0.1700

Data Index: 1779908 (Open Web Text)

Max Activating Token Index: 171

Text #2

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.5713. Min Act: -0.1700

Data Index: 4720921 (Open Web Text)

Max Activating Token Index: 1007

Text #3

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.5775. Min Act: -0.1700

Data Index: 8178843 (Open Web Text)

Max Activating Token Index: 633

Text #4

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.5550. Min Act: -0.1700

Data Index: 3880112 (Open Web Text)

Max Activating Token Index: 121

Text #5

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.4735. Min Act: -0.1700

Data Index: 3687286 (Open Web Text)

Max Activating Token Index: 707

Text #6

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.4545. Min Act: -0.1700

Data Index: 8287157 (Open Web Text)

Max Activating Token Index: 974

Text #7

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.4632. Min Act: -0.1700

Data Index: 4556898 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.4682. Min Act: -0.1700

Data Index: 3249624 (Open Web Text)

Max Activating Token Index: 467

Text #9

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.4382. Min Act: -0.1700

Data Index: 8449594 (Open Web Text)

Max Activating Token Index: 975

Text #10

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.4511. Min Act: -0.1700

Data Index: 3211935 (Open Web Text)

Max Activating Token Index: 347

Text #11

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.4038. Min Act: -0.1700

Data Index: 8537908 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.4188. Min Act: -0.1700

Data Index: 6680938 (Open Web Text)

Max Activating Token Index: 219

Text #13

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.4295. Min Act: -0.1700

Data Index: 7305200 (Open Web Text)

Max Activating Token Index: 567

Text #14

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.3816. Min Act: -0.1700

Data Index: 2414114 (Open Web Text)

Max Activating Token Index: 208

Text #15

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.3959. Min Act: -0.1700

Data Index: 4498834 (Open Web Text)

Max Activating Token Index: 196

Text #16

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.3501. Min Act: -0.1700

Data Index: 3778859 (Open Web Text)

Max Activating Token Index: 585

Text #17

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.3968. Min Act: -0.1700

Data Index: 701992 (Open Web Text)

Max Activating Token Index: 119

Text #18

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.3336. Min Act: -0.1700

Data Index: 2805861 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 4.6532. Min Range: -4.6532

Max Act: 4.3577. Min Act: -0.1700

Data Index: 4596676 (Open Web Text)

Max Activating Token Index: 682