Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.8370. Min Act: -0.1700
Data Index: 2240259 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.5870. Min Act: -0.1700
Data Index: 6480436 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.5245. Min Act: -0.1700
Data Index: 8825002 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.2433. Min Act: -0.1700
Data Index: 8765927 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.1808. Min Act: -0.1700
Data Index: 8077459 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.1495. Min Act: -0.1700
Data Index: 7487452 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.1183. Min Act: -0.1700
Data Index: 1340960 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.1183. Min Act: -0.1700
Data Index: 3544533 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.0870. Min Act: -0.1700
Data Index: 1458625 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.0245. Min Act: -0.1700
Data Index: 5862567 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.0245. Min Act: -0.1700
Data Index: 4509517 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8370. Min Range: -7.8370
Max Act: 6.9933. Min Act: -0.1700
Data Index: 7290488 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8370. Min Range: -7.8370
Max Act: 6.9933. Min Act: -0.1700
Data Index: 3979052 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8370. Min Range: -7.8370
Max Act: 7.0245. Min Act: -0.1700
Data Index: 1604412 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8370. Min Range: -7.8370
Max Act: 6.9620. Min Act: -0.1700
Data Index: 3502121 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8370. Min Range: -7.8370
Max Act: 6.9933. Min Act: -0.1700
Data Index: 5153484 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8370. Min Range: -7.8370
Max Act: 6.9933. Min Act: -0.1700
Data Index: 7686037 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8370. Min Range: -7.8370
Max Act: 6.9933. Min Act: -0.1700
Data Index: 4011187 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8370. Min Range: -7.8370
Max Act: 6.9620. Min Act: -0.1700
Data Index: 1984831 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8370. Min Range: -7.8370
Max Act: 6.9308. Min Act: -0.1700
Data Index: 3061892 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19