Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.3467. Min Act: -0.1700
Data Index: 3583493 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.2842. Min Act: -0.1700
Data Index: 7612489 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.2529. Min Act: -0.1700
Data Index: 2545910 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.2529. Min Act: -0.1700
Data Index: 7540746 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.2529. Min Act: -0.1700
Data Index: 7249842 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.2217. Min Act: -0.1700
Data Index: 8398842 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.2217. Min Act: -0.1700
Data Index: 1737703 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.2217. Min Act: -0.1700
Data Index: 8635909 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.2217. Min Act: -0.1700
Data Index: 6971294 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.2217. Min Act: -0.1700
Data Index: 3583492 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.1904. Min Act: -0.1700
Data Index: 7530052 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.1904. Min Act: -0.1700
Data Index: 659922 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.1904. Min Act: -0.1700
Data Index: 4336912 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.1279. Min Act: -0.1700
Data Index: 7463477 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.1592. Min Act: -0.1700
Data Index: 5447163 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.1592. Min Act: -0.1700
Data Index: 8197425 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.1592. Min Act: -0.1700
Data Index: 4400835 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.1592. Min Act: -0.1700
Data Index: 4195307 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.1279. Min Act: -0.1700
Data Index: 7559959 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3467. Min Range: -6.3467
Max Act: 6.1592. Min Act: -0.1700
Data Index: 1923869 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19