Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1946 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.9910. Min Act: -0.1700
Data Index: 262249 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.7723. Min Act: -0.1700
Data Index: 50121 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.7098. Min Act: -0.1700
Data Index: 1244015 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6785. Min Act: -0.1700
Data Index: 811193 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.7098. Min Act: -0.1700
Data Index: 1066509 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.7410. Min Act: -0.1700
Data Index: 22181 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6785. Min Act: -0.1700
Data Index: 540687 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6785. Min Act: -0.1700
Data Index: 507812 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6785. Min Act: -0.1700
Data Index: 671602 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6160. Min Act: -0.1700
Data Index: 983162 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6473. Min Act: -0.1700
Data Index: 619053 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6785. Min Act: -0.1700
Data Index: 966975 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6785. Min Act: -0.1700
Data Index: 1006214 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6160. Min Act: -0.1700
Data Index: 303100 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6160. Min Act: -0.1700
Data Index: 886876 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.5848. Min Act: -0.1700
Data Index: 838373 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.5848. Min Act: -0.1700
Data Index: 633 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.5848. Min Act: -0.1700
Data Index: 126131 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.6160. Min Act: -0.1700
Data Index: 978368 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9910. Min Range: -4.9910
Max Act: 4.5535. Min Act: -0.1700
Data Index: 465293 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19