Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 727 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.7005. Min Act: -0.1700
Data Index: 172182 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.7005. Min Act: -0.1700
Data Index: 794486 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.7165. Min Act: -0.1700
Data Index: 1241902 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.7165. Min Act: -0.1700
Data Index: 86560 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.7325. Min Act: -0.1700
Data Index: 239911 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6524. Min Act: -0.1700
Data Index: 1059172 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6685. Min Act: -0.1700
Data Index: 1031063 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6364. Min Act: -0.1700
Data Index: 734375 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6524. Min Act: -0.1700
Data Index: 711354 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6524. Min Act: -0.1700
Data Index: 239338 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6845. Min Act: -0.1700
Data Index: 1358112 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6364. Min Act: -0.1700
Data Index: 1109720 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6042. Min Act: -0.1700
Data Index: 1087704 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6364. Min Act: -0.1700
Data Index: 1223075 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6685. Min Act: -0.1700
Data Index: 909447 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6524. Min Act: -0.1700
Data Index: 519276 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6042. Min Act: -0.1700
Data Index: 705193 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6364. Min Act: -0.1700
Data Index: 720854 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6203. Min Act: -0.1700
Data Index: 84002 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7325. Min Range: -2.7325
Max Act: 2.6042. Min Act: -0.1700
Data Index: 539175 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19