Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2041 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.4588. Min Act: -0.1700
Data Index: 3308215 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.4588. Min Act: -0.1700
Data Index: 5155353 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.3963. Min Act: -0.1700
Data Index: 53008 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.3651. Min Act: -0.1700
Data Index: 8772806 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.3651. Min Act: -0.1700
Data Index: 5798236 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.3338. Min Act: -0.1700
Data Index: 296026 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.3026. Min Act: -0.1700
Data Index: 6174511 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.3026. Min Act: -0.1700
Data Index: 744590 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.3026. Min Act: -0.1700
Data Index: 6158539 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.2713. Min Act: -0.1700
Data Index: 101866 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.2088. Min Act: -0.1700
Data Index: 6601218 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.2401. Min Act: -0.1700
Data Index: 5676372 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.2088. Min Act: -0.1700
Data Index: 5369916 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.2088. Min Act: -0.1700
Data Index: 1553131 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.2088. Min Act: -0.1700
Data Index: 319844 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.2088. Min Act: -0.1700
Data Index: 4298322 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.2088. Min Act: -0.1700
Data Index: 4327372 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.2088. Min Act: -0.1700
Data Index: 344093 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.2088. Min Act: -0.1700
Data Index: 5789965 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4588. Min Range: -5.4588
Max Act: 5.1776. Min Act: -0.1700
Data Index: 6946026 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19