Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1920 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.8211. Min Act: -0.1700
Data Index: 308402 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.8211. Min Act: -0.1700
Data Index: 354531 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.8211. Min Act: -0.1700
Data Index: 1183264 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.8051. Min Act: -0.1700
Data Index: 78725 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7892. Min Act: -0.1700
Data Index: 818632 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7892. Min Act: -0.1700
Data Index: 1576485 (Python Code)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7733. Min Act: -0.1700
Data Index: 665618 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7573. Min Act: -0.1700
Data Index: 552932 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7733. Min Act: -0.1700
Data Index: 672563 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7733. Min Act: -0.1700
Data Index: 822 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7573. Min Act: -0.1700
Data Index: 945436 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7573. Min Act: -0.1700
Data Index: 703350 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7733. Min Act: -0.1700
Data Index: 1032928 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7733. Min Act: -0.1700
Data Index: 815738 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7414. Min Act: -0.1700
Data Index: 722370 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7414. Min Act: -0.1700
Data Index: 1191788 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7254. Min Act: -0.1700
Data Index: 1175800 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7254. Min Act: -0.1700
Data Index: 811415 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7254. Min Act: -0.1700
Data Index: 553958 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8211. Min Range: -2.8211
Max Act: 2.7254. Min Act: -0.1700
Data Index: 510925 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19