Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3991 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.1253. Min Act: -0.1700
Data Index: 5491173 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.0941. Min Act: -0.1700
Data Index: 2134275 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.0941. Min Act: -0.1700
Data Index: 5008059 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.0628. Min Act: -0.1700
Data Index: 2236145 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.0316. Min Act: -0.1700
Data Index: 3827191 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.0003. Min Act: -0.1700
Data Index: 1821051 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.0003. Min Act: -0.1700
Data Index: 4589392 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1253. Min Range: -5.1253
Max Act: 5.0003. Min Act: -0.1700
Data Index: 1895945 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9691. Min Act: -0.1700
Data Index: 1619421 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9691. Min Act: -0.1700
Data Index: 1299488 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9691. Min Act: -0.1700
Data Index: 2189642 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9378. Min Act: -0.1700
Data Index: 4455961 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9691. Min Act: -0.1700
Data Index: 4107570 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9378. Min Act: -0.1700
Data Index: 6279362 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9066. Min Act: -0.1700
Data Index: 5534161 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9378. Min Act: -0.1700
Data Index: 2583530 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.8753. Min Act: -0.1700
Data Index: 4888554 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9066. Min Act: -0.1700
Data Index: 2771903 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9066. Min Act: -0.1699
Data Index: 429030 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1253. Min Range: -5.1253
Max Act: 4.9378. Min Act: -0.1700
Data Index: 95062 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19