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

Dataset: Open Web Text

Neuron 30 in Layer 2

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: 4.8633. Min Range: -4.8633

Max Act: 4.8349. Min Act: -0.1700

Data Index: 5487493 (Open Web Text)

Max Activating Token Index: 998

Text #1

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.8633. Min Act: -0.1700

Data Index: 2312157 (Open Web Text)

Max Activating Token Index: 145

Text #2

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.8240. Min Act: -0.1700

Data Index: 2980522 (Open Web Text)

Max Activating Token Index: 863

Text #3

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.8174. Min Act: -0.1700

Data Index: 2802431 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7903. Min Act: -0.1700

Data Index: 4921200 (Open Web Text)

Max Activating Token Index: 66

Text #5

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7787. Min Act: -0.1700

Data Index: 6154464 (Open Web Text)

Max Activating Token Index: 729

Text #6

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7958. Min Act: -0.1700

Data Index: 1526692 (Open Web Text)

Max Activating Token Index: 145

Text #7

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7620. Min Act: -0.1700

Data Index: 3376681 (Open Web Text)

Max Activating Token Index: 87

Text #8

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7957. Min Act: -0.1700

Data Index: 8775881 (Open Web Text)

Max Activating Token Index: 270

Text #9

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7578. Min Act: -0.1700

Data Index: 5347597 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7616. Min Act: -0.1700

Data Index: 3059850 (Open Web Text)

Max Activating Token Index: 209

Text #11

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7766. Min Act: -0.1700

Data Index: 8154220 (Open Web Text)

Max Activating Token Index: 84

Text #12

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7334. Min Act: -0.1700

Data Index: 5879025 (Open Web Text)

Max Activating Token Index: 277

Text #13

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7521. Min Act: -0.1700

Data Index: 7630495 (Open Web Text)

Max Activating Token Index: 49

Text #14

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7314. Min Act: -0.1700

Data Index: 6386073 (Open Web Text)

Max Activating Token Index: 105

Text #15

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7280. Min Act: -0.1700

Data Index: 2460570 (Open Web Text)

Max Activating Token Index: 1019

Text #16

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7211. Min Act: -0.1700

Data Index: 3685870 (Open Web Text)

Max Activating Token Index: 641

Text #17

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7593. Min Act: -0.1700

Data Index: 6674744 (Open Web Text)

Max Activating Token Index: 433

Text #18

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7627. Min Act: -0.1700

Data Index: 2142928 (Open Web Text)

Max Activating Token Index: 298

Text #19

Max Range: 4.8633. Min Range: -4.8633

Max Act: 4.7045. Min Act: -0.1700

Data Index: 5579715 (Open Web Text)

Max Activating Token Index: 12