Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1357 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.8742. Min Act: -0.1700
Data Index: 351835 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.5305. Min Act: -0.1700
Data Index: 1267015 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.5305. Min Act: -0.1700
Data Index: 736237 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.4054. Min Act: -0.1700
Data Index: 1034286 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.3742. Min Act: -0.1700
Data Index: 806366 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.2492. Min Act: -0.1700
Data Index: 872400 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.1867. Min Act: -0.1700
Data Index: 217953 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.2492. Min Act: -0.1700
Data Index: 485306 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.2804. Min Act: -0.1700
Data Index: 760938 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.2492. Min Act: -0.1700
Data Index: 692121 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.1554. Min Act: -0.1700
Data Index: 974371 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.2804. Min Act: -0.1700
Data Index: 962465 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.1867. Min Act: -0.1700
Data Index: 857164 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.2179. Min Act: -0.1700
Data Index: 177002 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.2179. Min Act: -0.1700
Data Index: 405779 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.1554. Min Act: -0.1700
Data Index: 236397 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.0616. Min Act: -0.1700
Data Index: 242889 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.1554. Min Act: -0.1700
Data Index: 305885 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.1867. Min Act: -0.1700
Data Index: 1128684 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8742. Min Range: -4.8742
Max Act: 4.0304. Min Act: -0.1700
Data Index: 153064 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19