Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2609 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.7564. Min Act: -0.1700
Data Index: 2121287 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.7251. Min Act: -0.1700
Data Index: 36918 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.6626. Min Act: -0.1700
Data Index: 6545275 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.6001. Min Act: -0.1700
Data Index: 8515407 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.5689. Min Act: -0.1700
Data Index: 1805389 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.5689. Min Act: -0.1700
Data Index: 6400872 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.5689. Min Act: -0.1700
Data Index: 3971741 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.5064. Min Act: -0.1700
Data Index: 6718263 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.5064. Min Act: -0.1700
Data Index: 3524565 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.5064. Min Act: -0.1700
Data Index: 8020155 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.4751. Min Act: -0.1700
Data Index: 7285592 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.4751. Min Act: -0.1700
Data Index: 4151846 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.4751. Min Act: -0.1700
Data Index: 4311295 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.4438. Min Act: -0.1700
Data Index: 5037616 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.4438. Min Act: -0.1700
Data Index: 3376108 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.4438. Min Act: -0.1700
Data Index: 4192787 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.4438. Min Act: -0.1700
Data Index: 2923030 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.4438. Min Act: -0.1700
Data Index: 3951865 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.3813. Min Act: -0.1700
Data Index: 4071679 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7564. Min Range: -4.7564
Max Act: 4.4126. Min Act: -0.1700
Data Index: 2396004 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19