Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2011 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3597. Min Act: -0.1700
Data Index: 1135778 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3433. Min Act: -0.1700
Data Index: 736452 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3105. Min Act: -0.1700
Data Index: 905627 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3269. Min Act: -0.1700
Data Index: 675542 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3269. Min Act: -0.1700
Data Index: 1305315 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3105. Min Act: -0.1700
Data Index: 690347 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3269. Min Act: -0.1700
Data Index: 871101 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3269. Min Act: -0.1700
Data Index: 1013823 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3105. Min Act: -0.1700
Data Index: 764582 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3105. Min Act: -0.1700
Data Index: 450694 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3105. Min Act: -0.1700
Data Index: 619072 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3105. Min Act: -0.1700
Data Index: 630735 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3269. Min Act: -0.1700
Data Index: 896494 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3105. Min Act: -0.1700
Data Index: 1038191 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.2940. Min Act: -0.1700
Data Index: 720176 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3105. Min Act: -0.1700
Data Index: 367961 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.3105. Min Act: -0.1700
Data Index: 882778 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.2940. Min Act: -0.1700
Data Index: 17101 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.2776. Min Act: -0.1700
Data Index: 1023261 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3597. Min Range: -2.3597
Max Act: 2.2940. Min Act: -0.1700
Data Index: 1062675 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19