Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1437 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.3405. Min Act: -0.1700

Data Index: 1610438 (Python Code)

Max Activating Token Index: 514

Text #1

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.3299. Min Act: -0.1700

Data Index: 1066925 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.3183. Min Act: -0.1700

Data Index: 996208 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.3281. Min Act: -0.1700

Data Index: 231430 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2974. Min Act: -0.1700

Data Index: 1361910 (Python Code)

Max Activating Token Index: 734

Text #5

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2480. Min Act: -0.1700

Data Index: 1163066 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2418. Min Act: -0.1700

Data Index: 1490072 (Python Code)

Max Activating Token Index: 112

Text #7

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2461. Min Act: -0.1700

Data Index: 1628298 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1436535 (Python Code)

Max Activating Token Index: 1020

Text #9

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2402. Min Act: -0.1700

Data Index: 1578853 (Python Code)

Max Activating Token Index: 397

Text #10

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2045. Min Act: -0.1700

Data Index: 1421476 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2409. Min Act: -0.1700

Data Index: 613302 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2296. Min Act: -0.1700

Data Index: 277880 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2090. Min Act: -0.1700

Data Index: 170644 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.1870. Min Act: -0.1700

Data Index: 633115 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.1891. Min Act: -0.1700

Data Index: 1365056 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.2084. Min Act: -0.1700

Data Index: 1371115 (Python Code)

Max Activating Token Index: 546

Text #17

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.1797. Min Act: -0.1699

Data Index: 147377 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.1886. Min Act: -0.1700

Data Index: 1376656 (Python Code)

Max Activating Token Index: 791

Text #19

Max Range: 3.3405. Min Range: -3.3405

Max Act: 3.1540. Min Act: -0.1700

Data Index: 1366945 (Python Code)

Max Activating Token Index: 121