Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2017 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.9585. Min Act: -0.1700
Data Index: 462752 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.9585. Min Act: -0.1700
Data Index: 1071827 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.8647. Min Act: -0.1700
Data Index: 58337 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.8022. Min Act: -0.1700
Data Index: 1150180 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.8334. Min Act: -0.1700
Data Index: 947170 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.8022. Min Act: -0.1700
Data Index: 1280863 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.8334. Min Act: -0.1700
Data Index: 729074 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.8022. Min Act: -0.1700
Data Index: 292538 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.8022. Min Act: -0.1700
Data Index: 1352854 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.8022. Min Act: -0.1700
Data Index: 249023 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.8022. Min Act: -0.1700
Data Index: 1019293 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.7397. Min Act: -0.1700
Data Index: 929303 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.7709. Min Act: -0.1700
Data Index: 1312545 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.7397. Min Act: -0.1700
Data Index: 105824 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.7397. Min Act: -0.1700
Data Index: 678341 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.7397. Min Act: -0.1700
Data Index: 76514 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.7709. Min Act: -0.1700
Data Index: 508988 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.7397. Min Act: -0.1700
Data Index: 933192 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.7397. Min Act: -0.1700
Data Index: 1073513 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9585. Min Range: -4.9585
Max Act: 4.7084. Min Act: -0.1700
Data Index: 182046 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19