Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1401 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.7865. Min Act: -0.1700
Data Index: 337499 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.7240. Min Act: -0.1700
Data Index: 56599 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.7240. Min Act: -0.1700
Data Index: 30865 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.6615. Min Act: -0.1700
Data Index: 471135 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.6928. Min Act: -0.1700
Data Index: 752814 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.5990. Min Act: -0.1700
Data Index: 1145050 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.5053. Min Act: -0.1700
Data Index: 1219782 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.5678. Min Act: -0.1700
Data Index: 828232 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.5053. Min Act: -0.1700
Data Index: 1008599 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.5365. Min Act: -0.1700
Data Index: 872780 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.4428. Min Act: -0.1700
Data Index: 787268 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.4740. Min Act: -0.1700
Data Index: 1052574 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.4740. Min Act: -0.1700
Data Index: 1003841 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.5678. Min Act: -0.1700
Data Index: 400200 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.4740. Min Act: -0.1700
Data Index: 651783 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.4115. Min Act: -0.1700
Data Index: 593176 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.4740. Min Act: -0.1700
Data Index: 1090607 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.4740. Min Act: -0.1700
Data Index: 149878 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.4740. Min Act: -0.1700
Data Index: 895243 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7865. Min Range: -4.7865
Max Act: 4.4740. Min Act: -0.1700
Data Index: 1174735 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19