Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.2503. Min Act: -0.1700
Data Index: 5209596 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.2006. Min Act: -0.1694
Data Index: 4128204 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.2006. Min Act: -0.1700
Data Index: 1270287 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.1840. Min Act: -0.1700
Data Index: 7574979 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.1507. Min Act: -0.1700
Data Index: 5814450 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.1507. Min Act: -0.1700
Data Index: 6301749 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.1341. Min Act: -0.1700
Data Index: 7400612 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.1173. Min Act: -0.1700
Data Index: 1246249 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.1006. Min Act: -0.1680
Data Index: 1611016 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0839. Min Act: -0.1684
Data Index: 1584684 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0839. Min Act: -0.1700
Data Index: 4000095 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0839. Min Act: -0.1673
Data Index: 425247 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0671. Min Act: -0.1700
Data Index: 5224841 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0839. Min Act: -0.1700
Data Index: 6465359 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0671. Min Act: -0.1644
Data Index: 8261189 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0671. Min Act: -0.1700
Data Index: 6597026 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0671. Min Act: -0.1685
Data Index: 6622251 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0503. Min Act: -0.1700
Data Index: 6027799 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0503. Min Act: -0.1693
Data Index: 4191228 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2503. Min Range: -2.2503
Max Act: 2.0334. Min Act: -0.1631
Data Index: 6604483 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19