Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 28 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.2540. Min Act: -0.1700
Data Index: 1350390 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.2540. Min Act: -0.1700
Data Index: 396124 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.2228. Min Act: -0.1700
Data Index: 547824 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.2228. Min Act: -0.1700
Data Index: 513707 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.2228. Min Act: -0.1700
Data Index: 60180 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1915. Min Act: -0.1700
Data Index: 977237 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.2540. Min Act: -0.1700
Data Index: 1069626 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1290. Min Act: -0.1700
Data Index: 439354 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1290. Min Act: -0.1700
Data Index: 2365 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1602. Min Act: -0.1700
Data Index: 891990 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1602. Min Act: -0.1700
Data Index: 88145 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1915. Min Act: -0.1700
Data Index: 225426 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1602. Min Act: -0.1700
Data Index: 265262 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1290. Min Act: -0.1700
Data Index: 624239 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1602. Min Act: -0.1700
Data Index: 315032 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1602. Min Act: -0.1700
Data Index: 840052 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1602. Min Act: -0.1700
Data Index: 610654 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1290. Min Act: -0.1700
Data Index: 815962 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.0977. Min Act: -0.1700
Data Index: 12690 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2540. Min Range: -4.2540
Max Act: 4.1290. Min Act: -0.1700
Data Index: 870765 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19