Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 472 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.7669. Min Act: -0.1700
Data Index: 474782 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.7669. Min Act: -0.1700
Data Index: 453347 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.7043. Min Act: -0.1700
Data Index: 1268752 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6730. Min Act: -0.1700
Data Index: 490820 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6730. Min Act: -0.1700
Data Index: 342747 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.7043. Min Act: -0.1700
Data Index: 1113984 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6730. Min Act: -0.1700
Data Index: 1220603 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.7043. Min Act: -0.1700
Data Index: 1071497 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6417. Min Act: -0.1700
Data Index: 905109 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6730. Min Act: -0.1700
Data Index: 929504 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6417. Min Act: -0.1700
Data Index: 1298202 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.5791. Min Act: -0.1700
Data Index: 1014225 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6417. Min Act: -0.1700
Data Index: 99892 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6417. Min Act: -0.1700
Data Index: 509324 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6730. Min Act: -0.1700
Data Index: 1209182 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.5791. Min Act: -0.1700
Data Index: 65391 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6104. Min Act: -0.1700
Data Index: 768300 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6417. Min Act: -0.1700
Data Index: 1102759 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6104. Min Act: -0.1700
Data Index: 1238720 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7669. Min Range: -3.7669
Max Act: 3.6417. Min Act: -0.1700
Data Index: 732984 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19