Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.6808. Min Act: -0.1700
Data Index: 504509 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.6721. Min Act: -0.1700
Data Index: 166153 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.6373. Min Act: -0.1696
Data Index: 8471518 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.6112. Min Act: -0.1700
Data Index: 8663110 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.6024. Min Act: -0.1693
Data Index: 8267975 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5937. Min Act: -0.1609
Data Index: 1247770 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5937. Min Act: -0.1700
Data Index: 3881451 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5762. Min Act: -0.1691
Data Index: 2718609 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5850. Min Act: -0.1700
Data Index: 7615961 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5937. Min Act: -0.1605
Data Index: 3028317 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5762. Min Act: -0.1700
Data Index: 7438830 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5762. Min Act: -0.1700
Data Index: 4502449 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5762. Min Act: -0.1700
Data Index: 6307225 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5762. Min Act: -0.1671
Data Index: 8036666 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5675. Min Act: -0.1693
Data Index: 6248185 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5675. Min Act: -0.1685
Data Index: 8815577 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5675. Min Act: -0.1699
Data Index: 950250 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5587. Min Act: -0.1691
Data Index: 5500054 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5587. Min Act: -0.1662
Data Index: 5333070 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6808. Min Range: -1.6808
Max Act: 1.5412. Min Act: -0.1700
Data Index: 5006282 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19