Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.3292. Min Act: -0.1700
Data Index: 1746507 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.2354. Min Act: -0.1700
Data Index: 524925 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.1417. Min Act: -0.1700
Data Index: 423641 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.1729. Min Act: -0.1700
Data Index: 3601950 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.1417. Min Act: -0.1700
Data Index: 3759972 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.1417. Min Act: -0.1700
Data Index: 2828116 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.1104. Min Act: -0.1700
Data Index: 1337917 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.1104. Min Act: -0.1700
Data Index: 4971821 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.1104. Min Act: -0.1700
Data Index: 2421158 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.0792. Min Act: -0.1700
Data Index: 7794024 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.0479. Min Act: -0.1700
Data Index: 1745634 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.0479. Min Act: -0.1700
Data Index: 5787451 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.0479. Min Act: -0.1700
Data Index: 2404016 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.0479. Min Act: -0.1700
Data Index: 4003060 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.0167. Min Act: -0.1700
Data Index: 4048505 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.0167. Min Act: -0.1700
Data Index: 5735786 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.0167. Min Act: -0.1700
Data Index: 3996280 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.0167. Min Act: -0.1700
Data Index: 3233110 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3292. Min Range: -4.3292
Max Act: 3.9541. Min Act: -0.1700
Data Index: 1706532 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3292. Min Range: -4.3292
Max Act: 4.0167. Min Act: -0.1700
Data Index: 3648752 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19