Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3510 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1623. Min Range: -8.1623
Max Act: 8.1623. Min Act: -0.1700
Data Index: 1468999 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1623. Min Range: -8.1623
Max Act: 8.0373. Min Act: -0.1700
Data Index: 4406578 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.9748. Min Act: -0.1700
Data Index: 7000628 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.7560. Min Act: -0.1700
Data Index: 6729928 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.7248. Min Act: -0.1700
Data Index: 4387685 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.6623. Min Act: -0.1700
Data Index: 1247325 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.6310. Min Act: -0.1700
Data Index: 2406458 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.5998. Min Act: -0.1700
Data Index: 1486757 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.6310. Min Act: -0.1700
Data Index: 6872094 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.5998. Min Act: -0.1700
Data Index: 2580311 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.5685. Min Act: -0.1700
Data Index: 5768582 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.5685. Min Act: -0.1700
Data Index: 2610763 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.5060. Min Act: -0.1700
Data Index: 1877554 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.5060. Min Act: -0.1700
Data Index: 4735478 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.5060. Min Act: -0.1700
Data Index: 6160097 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.4748. Min Act: -0.1700
Data Index: 1962802 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.4748. Min Act: -0.1700
Data Index: 7741475 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.4748. Min Act: -0.1700
Data Index: 5090778 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.4435. Min Act: -0.1700
Data Index: 3101848 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1623. Min Range: -8.1623
Max Act: 7.4435. Min Act: -0.1700
Data Index: 3330632 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19