Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3954 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1650. Min Range: -7.1650
Max Act: 7.1650. Min Act: -0.1700
Data Index: 1199622 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1650. Min Range: -7.1650
Max Act: 7.0713. Min Act: -0.1700
Data Index: 7929330 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1650. Min Range: -7.1650
Max Act: 7.0400. Min Act: -0.1700
Data Index: 6572009 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9775. Min Act: -0.1700
Data Index: 3061489 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9775. Min Act: -0.1700
Data Index: 5173639 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9775. Min Act: -0.1700
Data Index: 5755681 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9775. Min Act: -0.1700
Data Index: 5819539 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9463. Min Act: -0.1700
Data Index: 3202847 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9775. Min Act: -0.1699
Data Index: 5267063 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9463. Min Act: -0.1700
Data Index: 6544448 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9150. Min Act: -0.1700
Data Index: 938391 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9150. Min Act: -0.1700
Data Index: 3317835 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.8838. Min Act: -0.1700
Data Index: 3634847 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9150. Min Act: -0.1700
Data Index: 2788109 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.9150. Min Act: -0.1700
Data Index: 3973012 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.8838. Min Act: -0.1700
Data Index: 4581267 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.8838. Min Act: -0.1700
Data Index: 319735 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.8838. Min Act: -0.1700
Data Index: 596023 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.8838. Min Act: -0.1700
Data Index: 5640089 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1650. Min Range: -7.1650
Max Act: 6.8838. Min Act: -0.1700
Data Index: 3894178 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19