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

Dataset: Open Web Text

Neuron 2236 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: 2.5464. Min Range: -2.5464

Max Act: 2.5464. Min Act: -0.1700

Data Index: 7128300 (Open Web Text)

Max Activating Token Index: 808

Text #1

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.5140. Min Act: -0.1700

Data Index: 5347140 (Open Web Text)

Max Activating Token Index: 962

Text #2

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.4344. Min Act: -0.1700

Data Index: 510158 (Open Web Text)

Max Activating Token Index: 985

Text #3

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.4369. Min Act: -0.1700

Data Index: 3814811 (Open Web Text)

Max Activating Token Index: 382

Text #4

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.4146. Min Act: -0.1700

Data Index: 7907924 (Open Web Text)

Max Activating Token Index: 56

Text #5

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.4023. Min Act: -0.1700

Data Index: 3070001 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.4176. Min Act: -0.1700

Data Index: 4332216 (Open Web Text)

Max Activating Token Index: 881

Text #7

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3889. Min Act: -0.1700

Data Index: 5084970 (Open Web Text)

Max Activating Token Index: 732

Text #8

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3851. Min Act: -0.1700

Data Index: 8494946 (Open Web Text)

Max Activating Token Index: 990

Text #9

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3725. Min Act: -0.1700

Data Index: 7738516 (Open Web Text)

Max Activating Token Index: 442

Text #10

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3715. Min Act: -0.1700

Data Index: 1679281 (Open Web Text)

Max Activating Token Index: 975

Text #11

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3717. Min Act: -0.1700

Data Index: 2044911 (Open Web Text)

Max Activating Token Index: 503

Text #12

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3810. Min Act: -0.1700

Data Index: 8648142 (Open Web Text)

Max Activating Token Index: 941

Text #13

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3648. Min Act: -0.1700

Data Index: 7270090 (Open Web Text)

Max Activating Token Index: 583

Text #14

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3540. Min Act: -0.1700

Data Index: 4551464 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3615. Min Act: -0.1700

Data Index: 7497844 (Open Web Text)

Max Activating Token Index: 797

Text #16

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3342. Min Act: -0.1700

Data Index: 931792 (Open Web Text)

Max Activating Token Index: 690

Text #17

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3369. Min Act: -0.1700

Data Index: 3627729 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3397. Min Act: -0.1700

Data Index: 7953784 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 2.5464. Min Range: -2.5464

Max Act: 2.3336. Min Act: -0.1700

Data Index: 2852858 (Open Web Text)

Max Activating Token Index: 677