Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5947 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.5149. Min Act: -0.1700
Data Index: 352570 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.5149. Min Act: -0.1700
Data Index: 7618721 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.5149. Min Act: -0.1700
Data Index: 2395063 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.5774. Min Act: -0.1700
Data Index: 975536 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.5149. Min Act: -0.1700
Data Index: 8642960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.5149. Min Act: -0.1700
Data Index: 1034421 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.5149. Min Act: -0.1700
Data Index: 7024340 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.5149. Min Act: -0.1700
Data Index: 6984074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.4524. Min Act: -0.1700
Data Index: 8036784 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.4524. Min Act: -0.1700
Data Index: 8577019 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.4524. Min Act: -0.1700
Data Index: 4077070 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.4524. Min Act: -0.1700
Data Index: 5451232 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.4524. Min Act: -0.1700
Data Index: 4578880 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.4524. Min Act: -0.1700
Data Index: 5436694 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.4524. Min Act: -0.1700
Data Index: 7268868 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.3899. Min Act: -0.1700
Data Index: 5132783 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.3899. Min Act: -0.1700
Data Index: 4474994 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.3899. Min Act: -0.1700
Data Index: 4352680 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.3899. Min Act: -0.1700
Data Index: 3141436 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5774. Min Range: -9.5774
Max Act: 9.3899. Min Act: -0.1700
Data Index: 2815705 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19