Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2455 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.1354. Min Act: -0.1700
Data Index: 8686901 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.1197. Min Act: -0.1700
Data Index: 3615482 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0724. Min Act: -0.1700
Data Index: 4957369 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0724. Min Act: -0.1700
Data Index: 8393848 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0566. Min Act: -0.1700
Data Index: 1672943 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0566. Min Act: -0.1700
Data Index: 283606 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0566. Min Act: -0.1700
Data Index: 3728492 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0250. Min Act: -0.1700
Data Index: 3832457 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0250. Min Act: -0.1700
Data Index: 468971 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0250. Min Act: -0.1700
Data Index: 5097639 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0092. Min Act: -0.1700
Data Index: 7360669 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0092. Min Act: -0.1700
Data Index: 7366060 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0092. Min Act: -0.1700
Data Index: 4901552 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1354. Min Range: -3.1354
Max Act: 3.0092. Min Act: -0.1700
Data Index: 268095 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1354. Min Range: -3.1354
Max Act: 2.9776. Min Act: -0.1700
Data Index: 3387329 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1354. Min Range: -3.1354
Max Act: 2.9934. Min Act: -0.1700
Data Index: 6404171 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1354. Min Range: -3.1354
Max Act: 2.9934. Min Act: -0.1700
Data Index: 1537267 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1354. Min Range: -3.1354
Max Act: 2.9934. Min Act: -0.1700
Data Index: 7516060 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1354. Min Range: -3.1354
Max Act: 2.9934. Min Act: -0.1700
Data Index: 2310186 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1354. Min Range: -3.1354
Max Act: 2.9934. Min Act: -0.1700
Data Index: 1425429 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19