Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1409 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.4457. Min Act: -0.1700
Data Index: 653460 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.3051. Min Act: -0.1700
Data Index: 671984 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.3364. Min Act: -0.1700
Data Index: 1248961 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.3207. Min Act: -0.1700
Data Index: 1159258 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.3520. Min Act: -0.1700
Data Index: 1098769 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.3207. Min Act: -0.1700
Data Index: 334646 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.3364. Min Act: -0.1700
Data Index: 74223 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.3207. Min Act: -0.1700
Data Index: 1115223 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2738. Min Act: -0.1700
Data Index: 961422 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2738. Min Act: -0.1700
Data Index: 193171 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2895. Min Act: -0.1700
Data Index: 682349 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2582. Min Act: -0.1700
Data Index: 1406601 (Python Code)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2426. Min Act: -0.1700
Data Index: 324578 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2582. Min Act: -0.1700
Data Index: 1014421 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2426. Min Act: -0.1700
Data Index: 416001 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2582. Min Act: -0.1700
Data Index: 39203 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2738. Min Act: -0.1700
Data Index: 519748 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2738. Min Act: -0.1700
Data Index: 412199 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2895. Min Act: -0.1700
Data Index: 161986 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4457. Min Range: -4.4457
Max Act: 4.2426. Min Act: -0.1700
Data Index: 1147146 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19