Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 419 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.0160. Min Range: -5.0160
Max Act: 5.0160. Min Act: -0.1700
Data Index: 261876 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.8597. Min Act: -0.1700
Data Index: 1059924 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.7972. Min Act: -0.1700
Data Index: 528463 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.7972. Min Act: -0.1700
Data Index: 304636 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.7660. Min Act: -0.1700
Data Index: 1186360 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.6410. Min Act: -0.1700
Data Index: 558575 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.7347. Min Act: -0.1700
Data Index: 533786 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.6410. Min Act: -0.1700
Data Index: 692769 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.6097. Min Act: -0.1700
Data Index: 1205378 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.6097. Min Act: -0.1700
Data Index: 1262264 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.6097. Min Act: -0.1700
Data Index: 21952 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.6097. Min Act: -0.1700
Data Index: 422179 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.5785. Min Act: -0.1700
Data Index: 272250 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.5785. Min Act: -0.1700
Data Index: 752280 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.5785. Min Act: -0.1700
Data Index: 582876 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.5785. Min Act: -0.1700
Data Index: 759402 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.5472. Min Act: -0.1700
Data Index: 632611 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.5472. Min Act: -0.1700
Data Index: 697085 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.5785. Min Act: -0.1700
Data Index: 392059 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0160. Min Range: -5.0160
Max Act: 4.5160. Min Act: -0.1700
Data Index: 667066 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19