Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2355 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0325. Min Range: -1.0325
Max Act: 1.0325. Min Act: -0.1700
Data Index: 1210084 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0325. Min Range: -1.0325
Max Act: 1.0325. Min Act: -0.1700
Data Index: 3591133 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0325. Min Range: -1.0325
Max Act: 1.0151. Min Act: -0.1700
Data Index: 3805792 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0325. Min Range: -1.0325
Max Act: 1.0064. Min Act: -0.1700
Data Index: 3630387 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0325. Min Range: -1.0325
Max Act: 1.0064. Min Act: -0.1700
Data Index: 8372543 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0325. Min Range: -1.0325
Max Act: 1.0064. Min Act: -0.1700
Data Index: 1651851 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9977. Min Act: -0.1700
Data Index: 7518846 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9977. Min Act: -0.1700
Data Index: 5538238 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9891. Min Act: -0.1700
Data Index: 2890959 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9891. Min Act: -0.1700
Data Index: 46060 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9891. Min Act: -0.1700
Data Index: 1582920 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9891. Min Act: -0.1700
Data Index: 7526216 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9804. Min Act: -0.1700
Data Index: 8310177 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9804. Min Act: -0.1700
Data Index: 5380111 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9891. Min Act: -0.1700
Data Index: 204066 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9717. Min Act: -0.1700
Data Index: 4151504 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9717. Min Act: -0.1700
Data Index: 5743731 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9717. Min Act: -0.1700
Data Index: 7573124 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9631. Min Act: -0.1700
Data Index: 1811874 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0325. Min Range: -1.0325
Max Act: 0.9631. Min Act: -0.1700
Data Index: 7105002 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19