Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1506. Min Range: -6.1506
Max Act: 6.1506. Min Act: -0.1700
Data Index: 8220893 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1506. Min Range: -6.1506
Max Act: 6.1506. Min Act: -0.1700
Data Index: 7520834 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1506. Min Range: -6.1506
Max Act: 6.1193. Min Act: -0.1700
Data Index: 963609 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.9943. Min Act: -0.1700
Data Index: 7963400 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.9318. Min Act: -0.1700
Data Index: 7781388 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.9318. Min Act: -0.1700
Data Index: 8720372 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.9006. Min Act: -0.1700
Data Index: 3608872 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.9006. Min Act: -0.1700
Data Index: 2978300 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.8693. Min Act: -0.1700
Data Index: 416509 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.8693. Min Act: -0.1700
Data Index: 633867 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.8381. Min Act: -0.1700
Data Index: 8094093 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.8693. Min Act: -0.1700
Data Index: 7726372 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.8381. Min Act: -0.1700
Data Index: 5042423 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.8381. Min Act: -0.1700
Data Index: 2422083 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.8381. Min Act: -0.1700
Data Index: 627227 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.8068. Min Act: -0.1700
Data Index: 2603543 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.8068. Min Act: -0.1700
Data Index: 5714728 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.8068. Min Act: -0.1700
Data Index: 7764332 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.7756. Min Act: -0.1700
Data Index: 4049565 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1506. Min Range: -6.1506
Max Act: 5.7756. Min Act: -0.1700
Data Index: 201265 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19