Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1931 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4831. Min Range: -5.4831
Max Act: 5.4831. Min Act: -0.1700
Data Index: 6037560 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4831. Min Range: -5.4831
Max Act: 5.2331. Min Act: -0.1700
Data Index: 6037576 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4831. Min Range: -5.4831
Max Act: 5.2019. Min Act: -0.1700
Data Index: 1380384 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4831. Min Range: -5.4831
Max Act: 5.0769. Min Act: -0.1700
Data Index: 8195772 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9831. Min Act: -0.1700
Data Index: 605827 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9831. Min Act: -0.1700
Data Index: 134156 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9519. Min Act: -0.1700
Data Index: 6931395 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9206. Min Act: -0.1700
Data Index: 5552487 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9206. Min Act: -0.1700
Data Index: 2977934 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9206. Min Act: -0.1700
Data Index: 3048958 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9519. Min Act: -0.1700
Data Index: 5552503 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9206. Min Act: -0.1700
Data Index: 7549341 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9206. Min Act: -0.1700
Data Index: 6855841 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9206. Min Act: -0.1700
Data Index: 6215495 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9519. Min Act: -0.1700
Data Index: 1084202 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9206. Min Act: -0.1700
Data Index: 6938504 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9206. Min Act: -0.1700
Data Index: 3957508 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9206. Min Act: -0.1700
Data Index: 1961073 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.9206. Min Act: -0.1700
Data Index: 6931393 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4831. Min Range: -5.4831
Max Act: 4.8894. Min Act: -0.1700
Data Index: 1961077 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19