Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 860 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.9682. Min Act: -0.1700
Data Index: 940941 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.9682. Min Act: -0.1700
Data Index: 780060 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.9523. Min Act: -0.1700
Data Index: 1143128 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.9365. Min Act: -0.1700
Data Index: 523302 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.9365. Min Act: -0.1700
Data Index: 894400 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.9048. Min Act: -0.1700
Data Index: 54415 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.9048. Min Act: -0.1700
Data Index: 61548 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8889. Min Act: -0.1700
Data Index: 1243775 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8889. Min Act: -0.1700
Data Index: 941864 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8889. Min Act: -0.1700
Data Index: 141556 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8730. Min Act: -0.1700
Data Index: 1017544 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8730. Min Act: -0.1700
Data Index: 377137 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8730. Min Act: -0.1700
Data Index: 232471 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8730. Min Act: -0.1700
Data Index: 113678 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8730. Min Act: -0.1700
Data Index: 722777 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8730. Min Act: -0.1700
Data Index: 721126 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8572. Min Act: -0.1700
Data Index: 156266 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8572. Min Act: -0.1700
Data Index: 979525 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8572. Min Act: -0.1700
Data Index: 1099621 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9682. Min Range: -2.9682
Max Act: 2.8572. Min Act: -0.1700
Data Index: 1048536 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19