Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4288 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.7579. Min Act: -0.1700
Data Index: 5829423 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.6954. Min Act: -0.1700
Data Index: 3420676 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.6954. Min Act: -0.1700
Data Index: 5142224 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.6329. Min Act: -0.1700
Data Index: 8463385 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1853527 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.5704. Min Act: -0.1700
Data Index: 6884051 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.5704. Min Act: -0.1700
Data Index: 1082361 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.5704. Min Act: -0.1700
Data Index: 7496627 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.5079. Min Act: -0.1700
Data Index: 1130619 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4766. Min Act: -0.1700
Data Index: 1685228 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4766. Min Act: -0.1700
Data Index: 6460646 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4766. Min Act: -0.1700
Data Index: 2947572 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4454. Min Act: -0.1700
Data Index: 1485297 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4141. Min Act: -0.1700
Data Index: 4394852 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4141. Min Act: -0.1700
Data Index: 3538364 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4141. Min Act: -0.1700
Data Index: 4238958 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4141. Min Act: -0.1700
Data Index: 4285263 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.4141. Min Act: -0.1700
Data Index: 4152403 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.3829. Min Act: -0.1700
Data Index: 2679613 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7579. Min Range: -5.7579
Max Act: 5.3829. Min Act: -0.1700
Data Index: 6505769 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19