Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 175 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.9684. Min Act: -0.1700
Data Index: 572604 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.8733. Min Act: -0.1700
Data Index: 158785 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.8097. Min Act: -0.1700
Data Index: 964623 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7938. Min Act: -0.1700
Data Index: 569914 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7938. Min Act: -0.1700
Data Index: 38759 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7778. Min Act: -0.1700
Data Index: 695481 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7778. Min Act: -0.1700
Data Index: 518948 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7619. Min Act: -0.1700
Data Index: 1062466 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7619. Min Act: -0.1700
Data Index: 1305923 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7619. Min Act: -0.1700
Data Index: 251103 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7459. Min Act: -0.1700
Data Index: 677039 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7300. Min Act: -0.1700
Data Index: 126784 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7619. Min Act: -0.1700
Data Index: 350717 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7459. Min Act: -0.1700
Data Index: 735401 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7459. Min Act: -0.1700
Data Index: 787313 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7459. Min Act: -0.1700
Data Index: 377399 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7619. Min Act: -0.1700
Data Index: 816566 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7459. Min Act: -0.1700
Data Index: 92261 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7300. Min Act: -0.1700
Data Index: 772406 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9684. Min Range: -2.9684
Max Act: 2.7300. Min Act: -0.1700
Data Index: 337687 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19