Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5711 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0933. Min Range: -5.0933
Max Act: 5.0933. Min Act: -0.1700
Data Index: 633485 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0933. Min Range: -5.0933
Max Act: 5.0620. Min Act: -0.1700
Data Index: 3381921 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0933. Min Range: -5.0933
Max Act: 5.0308. Min Act: -0.1700
Data Index: 7343751 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.9995. Min Act: -0.1700
Data Index: 1640506 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.9995. Min Act: -0.1700
Data Index: 864603 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.9995. Min Act: -0.1700
Data Index: 3469405 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.9995. Min Act: -0.1700
Data Index: 2010374 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.9995. Min Act: -0.1700
Data Index: 4230590 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.9058. Min Act: -0.1700
Data Index: 6347113 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.9370. Min Act: -0.1700
Data Index: 7318505 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.9058. Min Act: -0.1700
Data Index: 728298 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.9058. Min Act: -0.1700
Data Index: 3940174 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.8745. Min Act: -0.1700
Data Index: 1372701 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.8433. Min Act: -0.1700
Data Index: 5984702 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.8745. Min Act: -0.1700
Data Index: 664763 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.8745. Min Act: -0.1700
Data Index: 460771 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.8433. Min Act: -0.1700
Data Index: 3413818 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.8120. Min Act: -0.1700
Data Index: 29914 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.8120. Min Act: -0.1700
Data Index: 6743480 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0933. Min Range: -5.0933
Max Act: 4.8120. Min Act: -0.1700
Data Index: 1586019 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19