Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1634 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.4281. Min Act: -0.1700
Data Index: 7376348 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.3344. Min Act: -0.1700
Data Index: 2414982 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.3031. Min Act: -0.1700
Data Index: 2633328 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2719. Min Act: -0.1700
Data Index: 3138540 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2406. Min Act: -0.1686
Data Index: 3925249 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2406. Min Act: -0.1700
Data Index: 767874 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2406. Min Act: -0.1700
Data Index: 2270038 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2406. Min Act: -0.1700
Data Index: 6749475 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2094. Min Act: -0.1700
Data Index: 5144944 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2094. Min Act: -0.1700
Data Index: 3518319 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2094. Min Act: -0.1700
Data Index: 3360862 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.1781. Min Act: -0.1699
Data Index: 206836 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2094. Min Act: -0.1700
Data Index: 5594788 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2094. Min Act: -0.1700
Data Index: 6956256 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2094. Min Act: -0.1700
Data Index: 3631852 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2094. Min Act: -0.1700
Data Index: 4171702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2094. Min Act: -0.1700
Data Index: 2711379 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2094. Min Act: -0.1700
Data Index: 827024 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2094. Min Act: -0.1700
Data Index: 5634567 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4281. Min Range: -5.4281
Max Act: 5.2406. Min Act: -0.1700
Data Index: 2576716 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19