Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1598 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.8724. Min Act: -0.1700
Data Index: 25096 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.8411. Min Act: -0.1700
Data Index: 768253 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.8411. Min Act: -0.1700
Data Index: 28277 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.8411. Min Act: -0.1700
Data Index: 473258 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.7786. Min Act: -0.1700
Data Index: 292908 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.7161. Min Act: -0.1700
Data Index: 866125 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.7474. Min Act: -0.1700
Data Index: 1168716 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.7474. Min Act: -0.1700
Data Index: 1247469 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.6536. Min Act: -0.1700
Data Index: 1120378 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.6536. Min Act: -0.1700
Data Index: 541431 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.5911. Min Act: -0.1700
Data Index: 593036 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.5599. Min Act: -0.1700
Data Index: 271062 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.6224. Min Act: -0.1700
Data Index: 586942 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.5286. Min Act: -0.1700
Data Index: 36434 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.5599. Min Act: -0.1700
Data Index: 295491 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.5911. Min Act: -0.1700
Data Index: 1090953 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.4974. Min Act: -0.1700
Data Index: 1055054 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.5286. Min Act: -0.1700
Data Index: 36762 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.5286. Min Act: -0.1700
Data Index: 1103892 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8724. Min Range: -4.8724
Max Act: 4.4974. Min Act: -0.1700
Data Index: 879555 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19