Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5643 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2572. Min Range: -6.2572
Max Act: 6.2572. Min Act: -0.1700
Data Index: 2606437 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2572. Min Range: -6.2572
Max Act: 6.0072. Min Act: -0.1700
Data Index: 1823579 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.9135. Min Act: -0.1700
Data Index: 8595943 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.8822. Min Act: -0.1700
Data Index: 7165621 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.8510. Min Act: -0.1700
Data Index: 6605721 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.8510. Min Act: -0.1700
Data Index: 1194165 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.8510. Min Act: -0.1700
Data Index: 7165623 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.8510. Min Act: -0.1700
Data Index: 2134674 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7572. Min Act: -0.1700
Data Index: 2317702 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7572. Min Act: -0.1700
Data Index: 7197664 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7572. Min Act: -0.1700
Data Index: 2610096 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7885. Min Act: -0.1700
Data Index: 2195509 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7260. Min Act: -0.1700
Data Index: 8623189 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.6947. Min Act: -0.1700
Data Index: 6490047 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.7572. Min Act: -0.1700
Data Index: 5404436 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.6947. Min Act: -0.1700
Data Index: 947863 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.6635. Min Act: -0.1700
Data Index: 3265271 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.6635. Min Act: -0.1700
Data Index: 4778717 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.6322. Min Act: -0.1700
Data Index: 2261038 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2572. Min Range: -6.2572
Max Act: 5.6010. Min Act: -0.1700
Data Index: 171672 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19