Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.4286. Min Act: -0.1700
Data Index: 700403 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 2891019 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 1318785 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 4318052 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 4197330 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 3984278 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 957366 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 68712 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 3780709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 3173082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 565598 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 1447237 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 637244 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 2274685 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 698551 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 537208 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 2243598 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1699
Data Index: 2096836 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 1114302 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4286. Min Range: -4.4286
Max Act: 4.3973. Min Act: -0.1700
Data Index: 1947692 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19