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

Dataset: Open Web Text

Neuron 2814 in Layer 4

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: 4.6958. Min Range: -4.6958

Max Act: 4.6958. Min Act: -0.1700

Data Index: 8787179 (Open Web Text)

Max Activating Token Index: 25

Text #1

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.6629. Min Act: -0.1700

Data Index: 7748075 (Open Web Text)

Max Activating Token Index: 169

Text #2

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.6160. Min Act: -0.1700

Data Index: 4710848 (Open Web Text)

Max Activating Token Index: 861

Text #3

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.6182. Min Act: -0.1700

Data Index: 4435545 (Open Web Text)

Max Activating Token Index: 802

Text #4

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.6072. Min Act: -0.1700

Data Index: 8469570 (Open Web Text)

Max Activating Token Index: 929

Text #5

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.6137. Min Act: -0.1700

Data Index: 8631429 (Open Web Text)

Max Activating Token Index: 813

Text #6

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.6051. Min Act: -0.1700

Data Index: 3164781 (Open Web Text)

Max Activating Token Index: 539

Text #7

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5945. Min Act: -0.1700

Data Index: 815846 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5788. Min Act: -0.1700

Data Index: 6247223 (Open Web Text)

Max Activating Token Index: 390

Text #9

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5547. Min Act: -0.1700

Data Index: 3050327 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5521. Min Act: -0.1700

Data Index: 8791857 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5751. Min Act: -0.1700

Data Index: 3246282 (Open Web Text)

Max Activating Token Index: 89

Text #12

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5393. Min Act: -0.1700

Data Index: 907506 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5690. Min Act: -0.1700

Data Index: 6962426 (Open Web Text)

Max Activating Token Index: 130

Text #14

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5454. Min Act: -0.1700

Data Index: 2749944 (Open Web Text)

Max Activating Token Index: 505

Text #15

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5268. Min Act: -0.1700

Data Index: 907505 (Open Web Text)

Max Activating Token Index: 330

Text #16

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5187. Min Act: -0.1700

Data Index: 2795906 (Open Web Text)

Max Activating Token Index: 897

Text #17

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.5078. Min Act: -0.1700

Data Index: 2752388 (Open Web Text)

Max Activating Token Index: 680

Text #18

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.4873. Min Act: -0.1700

Data Index: 7399004 (Open Web Text)

Max Activating Token Index: 556

Text #19

Max Range: 4.6958. Min Range: -4.6958

Max Act: 4.4976. Min Act: -0.1700

Data Index: 2070526 (Open Web Text)

Max Activating Token Index: 730