Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.5598. Min Act: -0.1700
Data Index: 470966 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.4973. Min Act: -0.1700
Data Index: 1278712 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.4660. Min Act: -0.1700
Data Index: 685196 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.4348. Min Act: -0.1700
Data Index: 1031091 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.3723. Min Act: -0.1700
Data Index: 1223236 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.3410. Min Act: -0.1700
Data Index: 316546 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.3410. Min Act: -0.1700
Data Index: 198546 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.2785. Min Act: -0.1700
Data Index: 1164729 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.3098. Min Act: -0.1700
Data Index: 434238 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.2473. Min Act: -0.1700
Data Index: 847110 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.2785. Min Act: -0.1700
Data Index: 1297844 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.2473. Min Act: -0.1700
Data Index: 490529 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.2473. Min Act: -0.1700
Data Index: 18594 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.2160. Min Act: -0.1700
Data Index: 180400 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.2160. Min Act: -0.1700
Data Index: 1227167 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.2473. Min Act: -0.1700
Data Index: 776476 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.1535. Min Act: -0.1700
Data Index: 1237406 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.2160. Min Act: -0.1700
Data Index: 1268620 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.2160. Min Act: -0.1700
Data Index: 892702 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5598. Min Range: -4.5598
Max Act: 4.1535. Min Act: -0.1700
Data Index: 563503 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19