Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.8725. Min Act: -0.1700
Data Index: 8005963 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7631. Min Act: -0.1700
Data Index: 5129217 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.7005. Min Act: -0.1700
Data Index: 5518086 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.6536. Min Act: -0.1700
Data Index: 8507355 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.6066. Min Act: -0.1700
Data Index: 7201030 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.5753. Min Act: -0.1700
Data Index: 606086 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.5440. Min Act: -0.1700
Data Index: 1535936 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.5440. Min Act: -0.1700
Data Index: 4125508 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.5284. Min Act: -0.1700
Data Index: 2838949 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.5127. Min Act: -0.1700
Data Index: 6827542 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.5127. Min Act: -0.1700
Data Index: 4843835 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.4657. Min Act: -0.1700
Data Index: 3676230 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.4500. Min Act: -0.1700
Data Index: 3628358 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.4500. Min Act: -0.1700
Data Index: 2875014 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.4344. Min Act: -0.1700
Data Index: 5411509 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.4344. Min Act: -0.1700
Data Index: 2171543 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.4187. Min Act: -0.1700
Data Index: 1378514 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.4187. Min Act: -0.1700
Data Index: 1871650 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.4030. Min Act: -0.1700
Data Index: 8086520 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8725. Min Range: -3.8725
Max Act: 3.4030. Min Act: -0.1700
Data Index: 2595188 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19