Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 59 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.9214. Min Act: -0.1700
Data Index: 437248 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.8589. Min Act: -0.1700
Data Index: 948240 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.9214. Min Act: -0.1700
Data Index: 1590449 (Python Code)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.8901. Min Act: -0.1700
Data Index: 63464 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.7339. Min Act: -0.1700
Data Index: 985064 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.7339. Min Act: -0.1700
Data Index: 202423 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.7339. Min Act: -0.1700
Data Index: 652106 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.6714. Min Act: -0.1700
Data Index: 1153054 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.7026. Min Act: -0.1700
Data Index: 313285 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.6401. Min Act: -0.1700
Data Index: 1347125 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.6401. Min Act: -0.1700
Data Index: 766680 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.6714. Min Act: -0.1700
Data Index: 1618532 (Python Code)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.6714. Min Act: -0.1700
Data Index: 216323 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.6714. Min Act: -0.1700
Data Index: 643704 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.6401. Min Act: -0.1700
Data Index: 1049460 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.5776. Min Act: -0.1700
Data Index: 626933 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.5464. Min Act: -0.1700
Data Index: 799450 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.5464. Min Act: -0.1700
Data Index: 940183 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.5464. Min Act: -0.1700
Data Index: 481200 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9214. Min Range: -4.9214
Max Act: 4.4839. Min Act: -0.1700
Data Index: 218259 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19