Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.8382. Min Act: -0.1700
Data Index: 4461006 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.7757. Min Act: -0.1700
Data Index: 4731538 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.7444. Min Act: -0.1700
Data Index: 66110 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6819. Min Act: -0.1700
Data Index: 7292228 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6507. Min Act: -0.1700
Data Index: 6220964 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6819. Min Act: -0.1700
Data Index: 7129895 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6194. Min Act: -0.1700
Data Index: 709083 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6507. Min Act: -0.1700
Data Index: 6412888 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6194. Min Act: -0.1700
Data Index: 5081599 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6194. Min Act: -0.1700
Data Index: 8443586 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6194. Min Act: -0.1700
Data Index: 4992357 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6194. Min Act: -0.1700
Data Index: 248250 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6194. Min Act: -0.1700
Data Index: 5595364 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.5882. Min Act: -0.1700
Data Index: 419022 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.5569. Min Act: -0.1700
Data Index: 1230124 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.6194. Min Act: -0.1700
Data Index: 6456911 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.5882. Min Act: -0.1700
Data Index: 1785678 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.5882. Min Act: -0.1700
Data Index: 7253360 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.5882. Min Act: -0.1700
Data Index: 4848371 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8382. Min Range: -4.8382
Max Act: 4.5882. Min Act: -0.1700
Data Index: 3805232 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19