Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 78 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.9036. Min Act: -0.1700
Data Index: 128079 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.8401. Min Act: -0.1700
Data Index: 505670 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.8083. Min Act: -0.1700
Data Index: 120623 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.7445. Min Act: -0.1700
Data Index: 42072 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.7445. Min Act: -0.1700
Data Index: 1355402 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.7445. Min Act: -0.1700
Data Index: 723023 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.7285. Min Act: -0.1700
Data Index: 842496 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.7126. Min Act: -0.1700
Data Index: 1122779 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6966. Min Act: -0.1700
Data Index: 1293067 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6966. Min Act: -0.1700
Data Index: 1203915 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6805. Min Act: -0.1700
Data Index: 154038 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6645. Min Act: -0.1700
Data Index: 1157165 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6645. Min Act: -0.1700
Data Index: 188871 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6485. Min Act: -0.1700
Data Index: 356688 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6324. Min Act: -0.1700
Data Index: 954661 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6324. Min Act: -0.1700
Data Index: 1299938 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6324. Min Act: -0.1700
Data Index: 442363 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6164. Min Act: -0.1700
Data Index: 705876 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6324. Min Act: -0.1700
Data Index: 1180622 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9036. Min Range: -2.9036
Max Act: 2.6324. Min Act: -0.1700
Data Index: 648862 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19