Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5203 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2307. Min Range: -3.2307
Max Act: 3.2307. Min Act: -0.1700
Data Index: 3966610 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2307. Min Range: -3.2307
Max Act: 3.1521. Min Act: -0.1700
Data Index: 2011664 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2307. Min Range: -3.2307
Max Act: 3.1206. Min Act: -0.1700
Data Index: 1114909 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2307. Min Range: -3.2307
Max Act: 3.0733. Min Act: -0.1700
Data Index: 5293681 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2307. Min Range: -3.2307
Max Act: 3.0733. Min Act: -0.1700
Data Index: 3212827 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2307. Min Range: -3.2307
Max Act: 3.0418. Min Act: -0.1700
Data Index: 154772 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9944. Min Act: -0.1700
Data Index: 167088 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9944. Min Act: -0.1700
Data Index: 1422866 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2307. Min Range: -3.2307
Max Act: 3.0102. Min Act: -0.1700
Data Index: 1983425 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9944. Min Act: -0.1700
Data Index: 444835 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9944. Min Act: -0.1700
Data Index: 5125247 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9944. Min Act: -0.1700
Data Index: 8451796 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9944. Min Act: -0.1700
Data Index: 8251788 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9627. Min Act: -0.1700
Data Index: 2067952 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9786. Min Act: -0.1700
Data Index: 3799184 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9786. Min Act: -0.1700
Data Index: 5934189 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9627. Min Act: -0.1700
Data Index: 7181374 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9627. Min Act: -0.1700
Data Index: 5032164 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9627. Min Act: -0.1700
Data Index: 2886868 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2307. Min Range: -3.2307
Max Act: 2.9627. Min Act: -0.1700
Data Index: 3387573 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19