Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4703 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.8484. Min Act: -0.1700
Data Index: 1768797 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.8171. Min Act: -0.1700
Data Index: 2065907 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7234. Min Act: -0.1700
Data Index: 526694 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7234. Min Act: -0.1700
Data Index: 3368682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7234. Min Act: -0.1700
Data Index: 5769988 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7234. Min Act: -0.1700
Data Index: 4258097 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7234. Min Act: -0.1700
Data Index: 3109801 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.6609. Min Act: -0.1700
Data Index: 4281573 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.6609. Min Act: -0.1700
Data Index: 3701056 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.6609. Min Act: -0.1700
Data Index: 6942792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.6296. Min Act: -0.1700
Data Index: 3816384 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5984. Min Act: -0.1700
Data Index: 2263184 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5984. Min Act: -0.1700
Data Index: 3711438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5671. Min Act: -0.1700
Data Index: 1271769 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5984. Min Act: -0.1700
Data Index: 4725791 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5671. Min Act: -0.1700
Data Index: 1112714 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5671. Min Act: -0.1699
Data Index: 3149846 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5671. Min Act: -0.1700
Data Index: 3307361 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5671. Min Act: -0.1700
Data Index: 2156618 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5671. Min Act: -0.1700
Data Index: 1435381 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19