Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.2328. Min Act: -0.1700
Data Index: 3967856 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.2016. Min Act: -0.1700
Data Index: 834848 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.1391. Min Act: -0.1700
Data Index: 2763632 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.1078. Min Act: -0.1700
Data Index: 3314274 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.1078. Min Act: -0.1700
Data Index: 1215527 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.1078. Min Act: -0.1700
Data Index: 5939213 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.1078. Min Act: -0.1700
Data Index: 8279118 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.1078. Min Act: -0.1700
Data Index: 8439116 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0765. Min Act: -0.1699
Data Index: 4206648 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0765. Min Act: -0.1694
Data Index: 4350209 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0453. Min Act: -0.1700
Data Index: 6853521 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0765. Min Act: -0.1700
Data Index: 2640800 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0765. Min Act: -0.1700
Data Index: 8709309 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0453. Min Act: -0.1700
Data Index: 8467475 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0453. Min Act: -0.1699
Data Index: 6988299 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0453. Min Act: -0.1700
Data Index: 2062347 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0453. Min Act: -0.1700
Data Index: 1789995 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0453. Min Act: -0.1700
Data Index: 4734603 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0453. Min Act: -0.1700
Data Index: 6340200 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2328. Min Range: -4.2328
Max Act: 4.0140. Min Act: -0.1700
Data Index: 5982704 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19