Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2596. Min Range: -3.2596
Max Act: 3.2596. Min Act: -0.1700
Data Index: 8080499 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2596. Min Range: -3.2596
Max Act: 3.1023. Min Act: -0.1700
Data Index: 6058280 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2596. Min Range: -3.2596
Max Act: 3.0865. Min Act: -0.1700
Data Index: 3464714 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2596. Min Range: -3.2596
Max Act: 3.0707. Min Act: -0.1700
Data Index: 7312530 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.9443. Min Act: -0.1700
Data Index: 924182 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.9443. Min Act: -0.1700
Data Index: 5660342 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.9443. Min Act: -0.1700
Data Index: 3700791 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.9443. Min Act: -0.1700
Data Index: 3844527 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.9443. Min Act: -0.1700
Data Index: 8422461 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.9443. Min Act: -0.1700
Data Index: 3847387 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.9285. Min Act: -0.1700
Data Index: 6038056 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.9126. Min Act: -0.1700
Data Index: 4538382 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.8968. Min Act: -0.1700
Data Index: 4686706 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.9126. Min Act: -0.1700
Data Index: 1921539 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.8968. Min Act: -0.1700
Data Index: 4062745 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.8968. Min Act: -0.1700
Data Index: 5543237 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.8968. Min Act: -0.1700
Data Index: 5042052 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.8968. Min Act: -0.1700
Data Index: 3346554 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.9126. Min Act: -0.1700
Data Index: 5011589 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2596. Min Range: -3.2596
Max Act: 2.8968. Min Act: -0.1700
Data Index: 1871638 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19