Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.8397. Min Act: -0.1700
Data Index: 20838 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.7460. Min Act: -0.1700
Data Index: 201147 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.7147. Min Act: -0.1700
Data Index: 776395 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.7772. Min Act: -0.1700
Data Index: 1095121 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.7147. Min Act: -0.1700
Data Index: 478752 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.7147. Min Act: -0.1700
Data Index: 982365 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.6522. Min Act: -0.1700
Data Index: 682774 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.7460. Min Act: -0.1700
Data Index: 332753 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.7460. Min Act: -0.1700
Data Index: 1084766 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.6522. Min Act: -0.1700
Data Index: 1041125 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.6210. Min Act: -0.1700
Data Index: 640254 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.6210. Min Act: -0.1700
Data Index: 1067680 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.6210. Min Act: -0.1700
Data Index: 1248026 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.5585. Min Act: -0.1700
Data Index: 856487 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.5897. Min Act: -0.1700
Data Index: 530597 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.5585. Min Act: -0.1700
Data Index: 976262 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.5585. Min Act: -0.1700
Data Index: 574659 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.5272. Min Act: -0.1700
Data Index: 1082711 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.5272. Min Act: -0.1700
Data Index: 656540 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8397. Min Range: -4.8397
Max Act: 4.5585. Min Act: -0.1700
Data Index: 776990 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19