Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9627. Min Act: -0.1700
Data Index: 3402607 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9627. Min Act: -0.1700
Data Index: 4314916 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9314. Min Act: -0.1700
Data Index: 2092750 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9314. Min Act: -0.1700
Data Index: 1575589 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9002. Min Act: -0.1700
Data Index: 9591 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9002. Min Act: -0.1700
Data Index: 446373 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9002. Min Act: -0.1700
Data Index: 3965939 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9002. Min Act: -0.1700
Data Index: 5260553 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9002. Min Act: -0.1700
Data Index: 4544552 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9002. Min Act: -0.1700
Data Index: 4708148 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9002. Min Act: -0.1700
Data Index: 8904 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9002. Min Act: -0.1700
Data Index: 1556190 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9002. Min Act: -0.1700
Data Index: 3278427 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.8689. Min Act: -0.1700
Data Index: 5198083 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.9002. Min Act: -0.1700
Data Index: 1783289 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.8377. Min Act: -0.1700
Data Index: 7579106 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.8689. Min Act: -0.1700
Data Index: 7183704 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.8064. Min Act: -0.1700
Data Index: 4832461 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.8377. Min Act: -0.1700
Data Index: 3300044 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9627. Min Range: -4.9627
Max Act: 4.8377. Min Act: -0.1700
Data Index: 2795470 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19