Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 25 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.5673. Min Act: -0.1700
Data Index: 628777 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.5673. Min Act: -0.1700
Data Index: 2416 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.5512. Min Act: -0.1700
Data Index: 433001 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.5027. Min Act: -0.1700
Data Index: 294715 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4865. Min Act: -0.1700
Data Index: 1220594 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4540. Min Act: -0.1700
Data Index: 254762 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4540. Min Act: -0.1700
Data Index: 1041577 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4540. Min Act: -0.1700
Data Index: 21723 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4378. Min Act: -0.1700
Data Index: 800604 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4378. Min Act: -0.1700
Data Index: 1181231 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4378. Min Act: -0.1700
Data Index: 1198447 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4378. Min Act: -0.1700
Data Index: 351243 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4215. Min Act: -0.1700
Data Index: 1195019 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4215. Min Act: -0.1700
Data Index: 526977 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4215. Min Act: -0.1700
Data Index: 366076 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4378. Min Act: -0.1700
Data Index: 157015 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4215. Min Act: -0.1700
Data Index: 448752 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4215. Min Act: -0.1700
Data Index: 434612 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4378. Min Act: -0.1700
Data Index: 111798 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5673. Min Range: -2.5673
Max Act: 2.4215. Min Act: -0.1700
Data Index: 80352 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19