Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 629 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.4963. Min Act: -0.1700
Data Index: 372698 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3713. Min Act: -0.1694
Data Index: 6527559 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3401. Min Act: -0.1700
Data Index: 6465882 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3401. Min Act: -0.1697
Data Index: 6574702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3401. Min Act: -0.1700
Data Index: 6993791 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3401. Min Act: -0.1700
Data Index: 238110 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3401. Min Act: -0.1699
Data Index: 1475376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3401. Min Act: -0.1698
Data Index: 5305376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3401. Min Act: -0.1699
Data Index: 3520917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3088. Min Act: -0.1700
Data Index: 1282248 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3088. Min Act: -0.1700
Data Index: 459462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3088. Min Act: -0.1697
Data Index: 5374086 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3088. Min Act: -0.1699
Data Index: 3972116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3088. Min Act: -0.1700
Data Index: 3910984 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3088. Min Act: -0.1700
Data Index: 3447807 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3088. Min Act: -0.1700
Data Index: 3359742 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3088. Min Act: -0.1700
Data Index: 909779 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.2776. Min Act: -0.1700
Data Index: 3250936 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3088. Min Act: -0.1700
Data Index: 5162898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4963. Min Range: -4.4963
Max Act: 4.3088. Min Act: -0.1700
Data Index: 2567758 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19