Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1983 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.8765. Min Act: -0.1700
Data Index: 1340679 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.8606. Min Act: -0.1700
Data Index: 696964 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.8606. Min Act: -0.1700
Data Index: 698022 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.8288. Min Act: -0.1700
Data Index: 833777 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.8288. Min Act: -0.1700
Data Index: 1020606 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.8129. Min Act: -0.1700
Data Index: 1020642 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7969. Min Act: -0.1700
Data Index: 423649 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7969. Min Act: -0.1700
Data Index: 424962 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7969. Min Act: -0.1700
Data Index: 436719 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7810. Min Act: -0.1700
Data Index: 243356 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7810. Min Act: -0.1700
Data Index: 170277 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7651. Min Act: -0.1700
Data Index: 1041911 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7810. Min Act: -0.1700
Data Index: 1337892 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7810. Min Act: -0.1700
Data Index: 967090 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7810. Min Act: -0.1700
Data Index: 655190 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7969. Min Act: -0.1700
Data Index: 329811 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7491. Min Act: -0.1700
Data Index: 721149 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7651. Min Act: -0.1700
Data Index: 335563 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7651. Min Act: -0.1700
Data Index: 670434 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8765. Min Range: -2.8765
Max Act: 2.7651. Min Act: -0.1700
Data Index: 465445 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19