Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.8709. Min Act: -0.1700
Data Index: 7131976 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.7914. Min Act: -0.1700
Data Index: 3807371 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.8868. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.7755. Min Act: -0.1700
Data Index: 5577814 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.7755. Min Act: -0.1700
Data Index: 5642076 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.7276. Min Act: -0.1700
Data Index: 4824823 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.7595. Min Act: -0.1700
Data Index: 7374759 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.7276. Min Act: -0.1700
Data Index: 3204321 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.7276. Min Act: -0.1700
Data Index: 3312451 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.6956. Min Act: -0.1700
Data Index: 2083926 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.6956. Min Act: -0.1700
Data Index: 5050608 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.7116. Min Act: -0.1700
Data Index: 3482122 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.6956. Min Act: -0.1700
Data Index: 8721924 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.6956. Min Act: -0.1700
Data Index: 2264030 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.6796. Min Act: -0.1700
Data Index: 3775189 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.6796. Min Act: -0.1700
Data Index: 4465935 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.6796. Min Act: -0.1700
Data Index: 2599714 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.6636. Min Act: -0.1700
Data Index: 7180705 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.6796. Min Act: -0.1700
Data Index: 3510277 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8868. Min Range: -2.8868
Max Act: 2.6796. Min Act: -0.1700
Data Index: 7268223 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19