Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.7478. Min Act: -0.1700
Data Index: 805384 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.6383. Min Act: -0.1700
Data Index: 4091140 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.6540. Min Act: -0.1700
Data Index: 38671 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.6227. Min Act: -0.1700
Data Index: 4170385 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.6383. Min Act: -0.1700
Data Index: 2684988 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.6070. Min Act: -0.1700
Data Index: 454560 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.5601. Min Act: -0.1700
Data Index: 1674281 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.5287. Min Act: -0.1700
Data Index: 2204969 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.5287. Min Act: -0.1700
Data Index: 6526867 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.5287. Min Act: -0.1700
Data Index: 1800939 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.4974. Min Act: -0.1700
Data Index: 1502112 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.5131. Min Act: -0.1700
Data Index: 4661071 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.4974. Min Act: -0.1700
Data Index: 1969353 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.4818. Min Act: -0.1700
Data Index: 5667512 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.4818. Min Act: -0.1700
Data Index: 1623860 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.4661. Min Act: -0.1700
Data Index: 5716617 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.4661. Min Act: -0.1700
Data Index: 4112222 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.4661. Min Act: -0.1700
Data Index: 4658059 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.4504. Min Act: -0.1700
Data Index: 6033570 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7478. Min Range: -3.7478
Max Act: 3.4504. Min Act: -0.1700
Data Index: 624016 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19