Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.5948. Min Act: -0.1700
Data Index: 132848 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.5303. Min Act: -0.1700
Data Index: 303511 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.5141. Min Act: -0.1700
Data Index: 624377 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4655. Min Act: -0.1700
Data Index: 376401 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4817. Min Act: -0.1700
Data Index: 489030 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4817. Min Act: -0.1700
Data Index: 208510 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4655. Min Act: -0.1700
Data Index: 1629481 (Python Code)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4655. Min Act: -0.1700
Data Index: 811132 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4655. Min Act: -0.1700
Data Index: 1145331 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4492. Min Act: -0.1700
Data Index: 489402 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4492. Min Act: -0.1700
Data Index: 358604 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4492. Min Act: -0.1700
Data Index: 1008105 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4492. Min Act: -0.1700
Data Index: 583019 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4330. Min Act: -0.1700
Data Index: 190549 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4330. Min Act: -0.1700
Data Index: 1348695 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4492. Min Act: -0.1700
Data Index: 416169 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4492. Min Act: -0.1700
Data Index: 480535 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4330. Min Act: -0.1700
Data Index: 700125 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4330. Min Act: -0.1700
Data Index: 1340867 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5948. Min Range: -2.5948
Max Act: 2.4167. Min Act: -0.1700
Data Index: 257330 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19