Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1791 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7989. Min Act: -0.1700
Data Index: 269025 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7830. Min Act: -0.1700
Data Index: 455079 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7511. Min Act: -0.1700
Data Index: 1316564 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7192. Min Act: -0.1700
Data Index: 1001022 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7351. Min Act: -0.1700
Data Index: 1063759 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7192. Min Act: -0.1700
Data Index: 577562 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7192. Min Act: -0.1700
Data Index: 924001 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7351. Min Act: -0.1700
Data Index: 441607 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7192. Min Act: -0.1700
Data Index: 223742 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7032. Min Act: -0.1700
Data Index: 216782 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.6711. Min Act: -0.1700
Data Index: 1235380 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7192. Min Act: -0.1700
Data Index: 307245 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7032. Min Act: -0.1700
Data Index: 593618 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.6872. Min Act: -0.1699
Data Index: 1084110 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.7032. Min Act: -0.1700
Data Index: 1074156 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.6711. Min Act: -0.1700
Data Index: 115731 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.6872. Min Act: -0.1700
Data Index: 883431 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.6872. Min Act: -0.1700
Data Index: 480026 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.6872. Min Act: -0.1700
Data Index: 783193 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7989. Min Range: -2.7989
Max Act: 2.6711. Min Act: -0.1700
Data Index: 259200 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19