Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1938 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2352. Min Range: -3.2352
Max Act: 3.2352. Min Act: -0.1700
Data Index: 566370 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2352. Min Range: -3.2352
Max Act: 3.2037. Min Act: -0.1700
Data Index: 599187 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2352. Min Range: -3.2352
Max Act: 3.1565. Min Act: -0.1700
Data Index: 137919 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2352. Min Range: -3.2352
Max Act: 3.1408. Min Act: -0.1700
Data Index: 1185797 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2352. Min Range: -3.2352
Max Act: 3.1092. Min Act: -0.1700
Data Index: 555373 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.9671. Min Act: -0.1700
Data Index: 248867 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.9037. Min Act: -0.1700
Data Index: 807407 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.8879. Min Act: -0.1700
Data Index: 113792 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.8879. Min Act: -0.1700
Data Index: 415484 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.8402. Min Act: -0.1700
Data Index: 348942 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.8402. Min Act: -0.1700
Data Index: 336027 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.8720. Min Act: -0.1700
Data Index: 150074 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.8243. Min Act: -0.1700
Data Index: 1233023 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.8561. Min Act: -0.1700
Data Index: 603273 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.7925. Min Act: -0.1700
Data Index: 635428 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.8084. Min Act: -0.1700
Data Index: 458989 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.7925. Min Act: -0.1700
Data Index: 428983 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.7765. Min Act: -0.1700
Data Index: 182618 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.7446. Min Act: -0.1700
Data Index: 836788 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2352. Min Range: -3.2352
Max Act: 2.8084. Min Act: -0.1700
Data Index: 883386 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19