Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1090 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.9463. Min Act: -0.1700
Data Index: 1214737 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.8526. Min Act: -0.1700
Data Index: 123181 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.8838. Min Act: -0.1700
Data Index: 79053 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.8526. Min Act: -0.1700
Data Index: 710919 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.8213. Min Act: -0.1700
Data Index: 932451 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.8213. Min Act: -0.1700
Data Index: 450431 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.7588. Min Act: -0.1700
Data Index: 1219764 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.8213. Min Act: -0.1700
Data Index: 1191092 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.7276. Min Act: -0.1700
Data Index: 574173 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.7276. Min Act: -0.1700
Data Index: 702635 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.7901. Min Act: -0.1700
Data Index: 1105272 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.7901. Min Act: -0.1700
Data Index: 1116758 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.7588. Min Act: -0.1700
Data Index: 285242 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.7276. Min Act: -0.1700
Data Index: 168903 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.7588. Min Act: -0.1700
Data Index: 912679 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.7276. Min Act: -0.1700
Data Index: 543260 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.7276. Min Act: -0.1700
Data Index: 750627 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.6963. Min Act: -0.1700
Data Index: 913432 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.6963. Min Act: -0.1700
Data Index: 425281 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9463. Min Range: -4.9463
Max Act: 4.6651. Min Act: -0.1700
Data Index: 815096 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19