Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 951 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5452. Min Act: -0.1700
Data Index: 252120 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5452. Min Act: -0.1700
Data Index: 372486 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5452. Min Act: -0.1700
Data Index: 1018243 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5291. Min Act: -0.1700
Data Index: 368950 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5291. Min Act: -0.1700
Data Index: 921358 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5129. Min Act: -0.1700
Data Index: 390958 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5291. Min Act: -0.1700
Data Index: 380119 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5129. Min Act: -0.1700
Data Index: 480430 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5129. Min Act: -0.1700
Data Index: 1179801 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5129. Min Act: -0.1700
Data Index: 1186268 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5129. Min Act: -0.1700
Data Index: 304365 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5129. Min Act: -0.1700
Data Index: 866140 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.5129. Min Act: -0.1700
Data Index: 1227444 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.4967. Min Act: -0.1700
Data Index: 679515 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.4805. Min Act: -0.1700
Data Index: 764567 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.4967. Min Act: -0.1700
Data Index: 771321 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.4967. Min Act: -0.1700
Data Index: 252970 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.4967. Min Act: -0.1700
Data Index: 776296 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.4967. Min Act: -0.1700
Data Index: 839971 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5452. Min Range: -2.5452
Max Act: 2.4967. Min Act: -0.1700
Data Index: 897861 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19