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

Dataset: Open Web Text

Neuron 1624 in Layer 1

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: 3.5414. Min Range: -3.5414

Max Act: 3.5414. Min Act: -0.1700

Data Index: 6484810 (Open Web Text)

Max Activating Token Index: 948

Text #1

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4589. Min Act: -0.1700

Data Index: 2150086 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4814. Min Act: -0.1700

Data Index: 7925262 (Open Web Text)

Max Activating Token Index: 821

Text #3

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4552. Min Act: -0.1700

Data Index: 7412464 (Open Web Text)

Max Activating Token Index: 535

Text #4

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4593. Min Act: -0.1700

Data Index: 957758 (Open Web Text)

Max Activating Token Index: 924

Text #5

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4638. Min Act: -0.1700

Data Index: 7673889 (Open Web Text)

Max Activating Token Index: 69

Text #6

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4364. Min Act: -0.1700

Data Index: 6764761 (Open Web Text)

Max Activating Token Index: 674

Text #7

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4598. Min Act: -0.1700

Data Index: 6393124 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4249. Min Act: -0.1700

Data Index: 7260921 (Open Web Text)

Max Activating Token Index: 67

Text #9

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4149. Min Act: -0.1700

Data Index: 2150085 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4180. Min Act: -0.1700

Data Index: 4566729 (Open Web Text)

Max Activating Token Index: 924

Text #11

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4270. Min Act: -0.1700

Data Index: 7031825 (Open Web Text)

Max Activating Token Index: 208

Text #12

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4117. Min Act: -0.1700

Data Index: 5905162 (Open Web Text)

Max Activating Token Index: 792

Text #13

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4115. Min Act: -0.1700

Data Index: 6453590 (Open Web Text)

Max Activating Token Index: 942

Text #14

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.4001. Min Act: -0.1700

Data Index: 7639157 (Open Web Text)

Max Activating Token Index: 128

Text #15

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.3958. Min Act: -0.1700

Data Index: 6432921 (Open Web Text)

Max Activating Token Index: 665

Text #16

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.3897. Min Act: -0.1700

Data Index: 4007669 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.3926. Min Act: -0.1700

Data Index: 3292883 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.3980. Min Act: -0.1700

Data Index: 4175918 (Open Web Text)

Max Activating Token Index: 340

Text #19

Max Range: 3.5414. Min Range: -3.5414

Max Act: 3.3800. Min Act: -0.1700

Data Index: 2715063 (Open Web Text)

Max Activating Token Index: 137