Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1040 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.3113. Min Act: -0.1700
Data Index: 8343858 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.1863. Min Act: -0.1700
Data Index: 8072126 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.1550. Min Act: -0.1700
Data Index: 4618349 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0925. Min Act: -0.1700
Data Index: 7015584 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0925. Min Act: -0.1700
Data Index: 586401 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0925. Min Act: -0.1700
Data Index: 6339664 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0613. Min Act: -0.1700
Data Index: 3600035 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3113. Min Range: -7.3113
Max Act: 7.0300. Min Act: -0.1700
Data Index: 2046769 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9363. Min Act: -0.1700
Data Index: 7086603 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9050. Min Act: -0.1700
Data Index: 4973713 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9363. Min Act: -0.1700
Data Index: 2201081 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9675. Min Act: -0.1700
Data Index: 3609161 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9363. Min Act: -0.1700
Data Index: 4628427 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9050. Min Act: -0.1700
Data Index: 4612968 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9050. Min Act: -0.1700
Data Index: 6579025 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9050. Min Act: -0.1700
Data Index: 2232503 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.8738. Min Act: -0.1700
Data Index: 8163464 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.9050. Min Act: -0.1700
Data Index: 3275848 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.8738. Min Act: -0.1700
Data Index: 7999190 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3113. Min Range: -7.3113
Max Act: 6.8425. Min Act: -0.1700
Data Index: 2789105 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19