Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5736 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.6612. Min Act: -0.1700
Data Index: 7323457 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.5987. Min Act: -0.1699
Data Index: 2135073 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.5674. Min Act: -0.1700
Data Index: 7161801 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.5362. Min Act: -0.1700
Data Index: 7277025 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.5049. Min Act: -0.1700
Data Index: 924799 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.5049. Min Act: -0.1700
Data Index: 3576997 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.5049. Min Act: -0.1700
Data Index: 6883061 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.5049. Min Act: -0.1700
Data Index: 60103 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4737. Min Act: -0.1700
Data Index: 4589545 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4424. Min Act: -0.1700
Data Index: 296156 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4737. Min Act: -0.1700
Data Index: 8303109 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4737. Min Act: -0.1699
Data Index: 1342580 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4737. Min Act: -0.1700
Data Index: 2269809 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4737. Min Act: -0.1700
Data Index: 7838267 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4424. Min Act: -0.1698
Data Index: 2342956 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4424. Min Act: -0.1700
Data Index: 7631253 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4737. Min Act: -0.1700
Data Index: 8665484 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4424. Min Act: -0.1700
Data Index: 3731616 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4424. Min Act: -0.1700
Data Index: 647354 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6612. Min Range: -5.6612
Max Act: 5.4112. Min Act: -0.1700
Data Index: 2563688 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19