Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 152 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1984. Min Range: -5.1984
Max Act: 5.1984. Min Act: -0.1700
Data Index: 1351087 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1984. Min Range: -5.1984
Max Act: 5.1047. Min Act: -0.1700
Data Index: 811422 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.9484. Min Act: -0.1700
Data Index: 440330 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.9484. Min Act: -0.1700
Data Index: 1324308 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.9484. Min Act: -0.1700
Data Index: 783770 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.9172. Min Act: -0.1700
Data Index: 391485 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8859. Min Act: -0.1700
Data Index: 783726 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.9484. Min Act: -0.1700
Data Index: 800858 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8859. Min Act: -0.1700
Data Index: 1181335 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.7922. Min Act: -0.1700
Data Index: 371064 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8547. Min Act: -0.1700
Data Index: 709704 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8547. Min Act: -0.1700
Data Index: 317776 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.7922. Min Act: -0.1700
Data Index: 234184 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8234. Min Act: -0.1700
Data Index: 575943 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8547. Min Act: -0.1700
Data Index: 1153347 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8234. Min Act: -0.1700
Data Index: 1057282 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8234. Min Act: -0.1700
Data Index: 667430 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8859. Min Act: -0.1700
Data Index: 952077 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8547. Min Act: -0.1700
Data Index: 517747 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1984. Min Range: -5.1984
Max Act: 4.8234. Min Act: -0.1700
Data Index: 894910 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19