Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4608 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.4522. Min Act: -0.1700
Data Index: 2009607 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.4052. Min Act: -0.1700
Data Index: 4425924 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.3895. Min Act: -0.1700
Data Index: 8456486 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.3738. Min Act: -0.1700
Data Index: 4153923 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.3738. Min Act: -0.1700
Data Index: 8176080 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.3581. Min Act: -0.1700
Data Index: 4147198 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.3268. Min Act: -0.1700
Data Index: 4374227 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.3268. Min Act: -0.1700
Data Index: 213574 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2954. Min Act: -0.1700
Data Index: 5663113 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2797. Min Act: -0.1700
Data Index: 34408 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2954. Min Act: -0.1700
Data Index: 7377754 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2954. Min Act: -0.1700
Data Index: 5532803 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2954. Min Act: -0.1700
Data Index: 435104 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2640. Min Act: -0.1700
Data Index: 6850114 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2797. Min Act: -0.1700
Data Index: 1220925 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2640. Min Act: -0.1700
Data Index: 533146 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2797. Min Act: -0.1700
Data Index: 2861261 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2482. Min Act: -0.1700
Data Index: 4120875 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2482. Min Act: -0.1700
Data Index: 4042852 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4522. Min Range: -3.4522
Max Act: 3.2482. Min Act: -0.1700
Data Index: 1214361 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19