Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4386 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.4963. Min Act: -0.1700
Data Index: 1885893 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.4338. Min Act: -0.1700
Data Index: 2558831 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.2776. Min Act: -0.1700
Data Index: 7055085 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.2463. Min Act: -0.1700
Data Index: 2565431 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.2151. Min Act: -0.1700
Data Index: 4003104 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.1838. Min Act: -0.1700
Data Index: 1982455 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.1525. Min Act: -0.1700
Data Index: 6723057 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.1525. Min Act: -0.1700
Data Index: 4502179 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.1213. Min Act: -0.1700
Data Index: 7322882 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.1213. Min Act: -0.1700
Data Index: 1915512 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.0900. Min Act: -0.1700
Data Index: 347797 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.0900. Min Act: -0.1700
Data Index: 8112146 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.0900. Min Act: -0.1700
Data Index: 5752172 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.0588. Min Act: -0.1700
Data Index: 3170227 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.0588. Min Act: -0.1700
Data Index: 7260628 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.0588. Min Act: -0.1700
Data Index: 7935618 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.0588. Min Act: -0.1700
Data Index: 4387323 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.0275. Min Act: -0.1700
Data Index: 6611393 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.0275. Min Act: -0.1700
Data Index: 4180050 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.0275. Min Act: -0.1700
Data Index: 7262483 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19