Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5196 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.7302. Min Act: -0.1700
Data Index: 3644976 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6990. Min Act: -0.1700
Data Index: 2571897 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6677. Min Act: -0.1700
Data Index: 8342114 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6677. Min Act: -0.1700
Data Index: 1206779 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6677. Min Act: -0.1700
Data Index: 2246228 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6677. Min Act: -0.1700
Data Index: 3550518 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6365. Min Act: -0.1700
Data Index: 4371646 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6365. Min Act: -0.1700
Data Index: 162402 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6365. Min Act: -0.1700
Data Index: 6271837 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6365. Min Act: -0.1700
Data Index: 8312188 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6365. Min Act: -0.1700
Data Index: 3333003 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6365. Min Act: -0.1700
Data Index: 328375 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6365. Min Act: -0.1700
Data Index: 7804545 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6365. Min Act: -0.1700
Data Index: 8737333 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6052. Min Act: -0.1700
Data Index: 8253194 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6052. Min Act: -0.1700
Data Index: 3426570 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6052. Min Act: -0.1700
Data Index: 910001 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6052. Min Act: -0.1700
Data Index: 4351318 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6052. Min Act: -0.1700
Data Index: 8196813 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7302. Min Range: -5.7302
Max Act: 5.6052. Min Act: -0.1700
Data Index: 1828137 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19