Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2865 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3824. Min Range: -9.3824
Max Act: 9.3824. Min Act: -0.1700
Data Index: 1267423 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.9449. Min Act: -0.1700
Data Index: 6390397 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.9449. Min Act: -0.1700
Data Index: 4352739 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.8199. Min Act: -0.1700
Data Index: 5213466 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.6324. Min Act: -0.1700
Data Index: 4258513 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.6324. Min Act: -0.1700
Data Index: 3119182 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.5699. Min Act: -0.1700
Data Index: 2446847 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.5699. Min Act: -0.1700
Data Index: 2994511 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.5074. Min Act: -0.1700
Data Index: 993079 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.5074. Min Act: -0.1700
Data Index: 6631277 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.4449. Min Act: -0.1700
Data Index: 6781776 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.4449. Min Act: -0.1700
Data Index: 7433991 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.4449. Min Act: -0.1700
Data Index: 7446704 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.3824. Min Act: -0.1700
Data Index: 1521491 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.3824. Min Act: -0.1700
Data Index: 1227691 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.3824. Min Act: -0.1700
Data Index: 2266104 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.3824. Min Act: -0.1700
Data Index: 7558593 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.3199. Min Act: -0.1700
Data Index: 5991148 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.2574. Min Act: -0.1700
Data Index: 27518 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3824. Min Range: -9.3824
Max Act: 8.2574. Min Act: -0.1700
Data Index: 3317456 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19