Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1487 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.7916. Min Act: -0.1700
Data Index: 389931 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.7603. Min Act: -0.1700
Data Index: 314672 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.7291. Min Act: -0.1700
Data Index: 420943 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.6666. Min Act: -0.1700
Data Index: 729053 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.6666. Min Act: -0.1700
Data Index: 722972 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.6666. Min Act: -0.1700
Data Index: 459033 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.6666. Min Act: -0.1700
Data Index: 369867 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.6666. Min Act: -0.1700
Data Index: 749038 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.6041. Min Act: -0.1700
Data Index: 1084054 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.6041. Min Act: -0.1700
Data Index: 418447 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.5728. Min Act: -0.1700
Data Index: 118320 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.5728. Min Act: -0.1700
Data Index: 461926 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.5103. Min Act: -0.1699
Data Index: 811140 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.5416. Min Act: -0.1699
Data Index: 123981 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.5103. Min Act: -0.1699
Data Index: 43038 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.5416. Min Act: -0.1700
Data Index: 43212 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.5728. Min Act: -0.1700
Data Index: 539584 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.5416. Min Act: -0.1700
Data Index: 290232 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.5416. Min Act: -0.1700
Data Index: 133429 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7916. Min Range: -4.7916
Max Act: 4.5728. Min Act: -0.1700
Data Index: 585654 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19