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

Dataset: Open Web Text

Neuron 1054 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: 5.4152. Min Range: -5.4152

Max Act: 5.4152. Min Act: -0.1700

Data Index: 4035315 (Open Web Text)

Max Activating Token Index: 485

Text #1

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.3102. Min Act: -0.1700

Data Index: 6402270 (Open Web Text)

Max Activating Token Index: 294

Text #2

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.2903. Min Act: -0.1700

Data Index: 5287567 (Open Web Text)

Max Activating Token Index: 681

Text #3

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.2902. Min Act: -0.1700

Data Index: 1283235 (Open Web Text)

Max Activating Token Index: 585

Text #4

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.2533. Min Act: -0.1700

Data Index: 7405024 (Open Web Text)

Max Activating Token Index: 609

Text #5

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.2789. Min Act: -0.1700

Data Index: 7358084 (Open Web Text)

Max Activating Token Index: 583

Text #6

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.2577. Min Act: -0.1700

Data Index: 1183838 (Open Web Text)

Max Activating Token Index: 583

Text #7

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1995. Min Act: -0.1700

Data Index: 8698780 (Open Web Text)

Max Activating Token Index: 389

Text #8

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.2009. Min Act: -0.1700

Data Index: 359092 (Open Web Text)

Max Activating Token Index: 966

Text #9

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1859. Min Act: -0.1700

Data Index: 3021169 (Open Web Text)

Max Activating Token Index: 208

Text #10

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1913. Min Act: -0.1700

Data Index: 275114 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1875. Min Act: -0.1700

Data Index: 2852606 (Open Web Text)

Max Activating Token Index: 440

Text #12

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1495. Min Act: -0.1700

Data Index: 5152793 (Open Web Text)

Max Activating Token Index: 958

Text #13

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.2075. Min Act: -0.1700

Data Index: 1474604 (Open Web Text)

Max Activating Token Index: 745

Text #14

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1999. Min Act: -0.1700

Data Index: 6647944 (Open Web Text)

Max Activating Token Index: 692

Text #15

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1689. Min Act: -0.1700

Data Index: 2451448 (Open Web Text)

Max Activating Token Index: 726

Text #16

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1697. Min Act: -0.1700

Data Index: 6049880 (Open Web Text)

Max Activating Token Index: 625

Text #17

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1532. Min Act: -0.1700

Data Index: 3690012 (Open Web Text)

Max Activating Token Index: 928

Text #18

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1312. Min Act: -0.1700

Data Index: 5071669 (Open Web Text)

Max Activating Token Index: 290

Text #19

Max Range: 5.4152. Min Range: -5.4152

Max Act: 5.1349. Min Act: -0.1700

Data Index: 4997675 (Open Web Text)

Max Activating Token Index: 767