Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1273 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.1766. Min Act: -0.1700
Data Index: 1208519 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.0829. Min Act: -0.1700
Data Index: 1337401 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1766. Min Range: -4.1766
Max Act: 4.0516. Min Act: -0.1700
Data Index: 633531 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9891. Min Act: -0.1700
Data Index: 462983 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9891. Min Act: -0.1700
Data Index: 62647 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9891. Min Act: -0.1700
Data Index: 83139 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9891. Min Act: -0.1700
Data Index: 770664 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9578. Min Act: -0.1700
Data Index: 1081653 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9265. Min Act: -0.1700
Data Index: 1163405 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9265. Min Act: -0.1700
Data Index: 1215103 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9265. Min Act: -0.1700
Data Index: 740111 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9265. Min Act: -0.1700
Data Index: 276338 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.8953. Min Act: -0.1700
Data Index: 1243385 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.8953. Min Act: -0.1700
Data Index: 508533 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9265. Min Act: -0.1700
Data Index: 1312959 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.8953. Min Act: -0.1700
Data Index: 219002 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.8953. Min Act: -0.1700
Data Index: 505658 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.8953. Min Act: -0.1700
Data Index: 319255 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.8640. Min Act: -0.1700
Data Index: 370672 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1766. Min Range: -4.1766
Max Act: 3.9265. Min Act: -0.1700
Data Index: 60823 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19