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

Dataset: Open Web Text

Neuron 2456 in Layer 3

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: 5.5088. Min Range: -5.5088

Max Act: 5.5063. Min Act: -0.1700

Data Index: 6449115 (Open Web Text)

Max Activating Token Index: 541

Text #1

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.5088. Min Act: -0.1700

Data Index: 4894204 (Open Web Text)

Max Activating Token Index: 322

Text #2

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.4495. Min Act: -0.1700

Data Index: 1421142 (Open Web Text)

Max Activating Token Index: 971

Text #3

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.4653. Min Act: -0.1700

Data Index: 4196833 (Open Web Text)

Max Activating Token Index: 580

Text #4

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.4069. Min Act: -0.1700

Data Index: 2991657 (Open Web Text)

Max Activating Token Index: 88

Text #5

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.3469. Min Act: -0.1700

Data Index: 1546668 (Open Web Text)

Max Activating Token Index: 583

Text #6

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.3620. Min Act: -0.1700

Data Index: 5165312 (Open Web Text)

Max Activating Token Index: 338

Text #7

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.3592. Min Act: -0.1700

Data Index: 1180708 (Open Web Text)

Max Activating Token Index: 304

Text #8

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.3261. Min Act: -0.1700

Data Index: 1472028 (Open Web Text)

Max Activating Token Index: 396

Text #9

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.3290. Min Act: -0.1700

Data Index: 6862810 (Open Web Text)

Max Activating Token Index: 150

Text #10

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.3532. Min Act: -0.1700

Data Index: 595803 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.3040. Min Act: -0.1700

Data Index: 7894273 (Open Web Text)

Max Activating Token Index: 65

Text #12

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.2949. Min Act: -0.1700

Data Index: 6444115 (Open Web Text)

Max Activating Token Index: 443

Text #13

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.3042. Min Act: -0.1700

Data Index: 3475339 (Open Web Text)

Max Activating Token Index: 377

Text #14

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.3313. Min Act: -0.1700

Data Index: 3592592 (Open Web Text)

Max Activating Token Index: 249

Text #15

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.2771. Min Act: -0.1700

Data Index: 2683866 (Open Web Text)

Max Activating Token Index: 468

Text #16

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.2683. Min Act: -0.1700

Data Index: 3153915 (Open Web Text)

Max Activating Token Index: 1004

Text #17

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.2844. Min Act: -0.1700

Data Index: 6404969 (Open Web Text)

Max Activating Token Index: 141

Text #18

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.2387. Min Act: -0.1700

Data Index: 2118824 (Open Web Text)

Max Activating Token Index: 166

Text #19

Max Range: 5.5088. Min Range: -5.5088

Max Act: 5.2395. Min Act: -0.1700

Data Index: 2438372 (Open Web Text)

Max Activating Token Index: 425