Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4608 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.5483. Min Act: -0.1700
Data Index: 6083478 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.4781. Min Act: -0.1700
Data Index: 3981067 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.4605. Min Act: -0.1700
Data Index: 2468935 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.4341. Min Act: -0.1700
Data Index: 7180868 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.4165. Min Act: -0.1700
Data Index: 6975799 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3989. Min Act: -0.1700
Data Index: 7268059 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3901. Min Act: -0.1700
Data Index: 6940821 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3901. Min Act: -0.1700
Data Index: 462491 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3813. Min Act: -0.1700
Data Index: 3833686 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3901. Min Act: -0.1700
Data Index: 2485117 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3901. Min Act: -0.1700
Data Index: 319443 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3725. Min Act: -0.1700
Data Index: 6074478 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3901. Min Act: -0.1700
Data Index: 474122 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3813. Min Act: -0.1700
Data Index: 4967909 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3725. Min Act: -0.1700
Data Index: 8495525 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3636. Min Act: -0.1700
Data Index: 7089777 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3636. Min Act: -0.1700
Data Index: 3985172 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3725. Min Act: -0.1700
Data Index: 6819603 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3636. Min Act: -0.1700
Data Index: 526454 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5483. Min Range: -1.5483
Max Act: 1.3725. Min Act: -0.1700
Data Index: 1219713 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19