Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 84 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.5663. Min Act: -0.1700
Data Index: 1138311 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.4530. Min Act: -0.1700
Data Index: 1340870 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.4204. Min Act: -0.1700
Data Index: 958104 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.3551. Min Act: -0.1700
Data Index: 150379 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.3223. Min Act: -0.1700
Data Index: 632696 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.3387. Min Act: -0.1700
Data Index: 115649 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.3387. Min Act: -0.1700
Data Index: 1109608 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.3387. Min Act: -0.1700
Data Index: 285190 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.3059. Min Act: -0.1700
Data Index: 228633 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.3059. Min Act: -0.1700
Data Index: 541457 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.3223. Min Act: -0.1700
Data Index: 194439 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.3387. Min Act: -0.1700
Data Index: 752888 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.3059. Min Act: -0.1700
Data Index: 1088093 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.2895. Min Act: -0.1700
Data Index: 42527 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.2895. Min Act: -0.1700
Data Index: 816449 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.2730. Min Act: -0.1700
Data Index: 22304 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.2730. Min Act: -0.1700
Data Index: 379843 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.2730. Min Act: -0.1700
Data Index: 903115 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.2730. Min Act: -0.1700
Data Index: 16252 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5663. Min Range: -2.5663
Max Act: 2.2730. Min Act: -0.1700
Data Index: 526278 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19