Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 53 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.4775. Min Act: -0.1700
Data Index: 586962 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.4775. Min Act: -0.1700
Data Index: 59717 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.1337. Min Act: -0.1700
Data Index: 147636 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2900. Min Act: -0.1700
Data Index: 966799 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2587. Min Act: -0.1700
Data Index: 1129726 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.3212. Min Act: -0.1700
Data Index: 1190116 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2587. Min Act: -0.1700
Data Index: 741687 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2275. Min Act: -0.1700
Data Index: 488944 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2587. Min Act: -0.1700
Data Index: 247672 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2587. Min Act: -0.1700
Data Index: 570741 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2275. Min Act: -0.1700
Data Index: 460327 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2275. Min Act: -0.1700
Data Index: 715682 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.1649. Min Act: -0.1700
Data Index: 974424 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2275. Min Act: -0.1700
Data Index: 548132 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2275. Min Act: -0.1700
Data Index: 166307 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.1962. Min Act: -0.1700
Data Index: 908837 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.1962. Min Act: -0.1700
Data Index: 573701 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.2587. Min Act: -0.1700
Data Index: 366092 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.0712. Min Act: -0.1700
Data Index: 856523 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4775. Min Range: -4.4775
Max Act: 4.1962. Min Act: -0.1700
Data Index: 239918 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19