Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2070 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0730. Min Range: -2.0730
Max Act: 2.0730. Min Act: -0.1699
Data Index: 1099758 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0730. Min Range: -2.0730
Max Act: 2.0730. Min Act: -0.1700
Data Index: 151180 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0730. Min Range: -2.0730
Max Act: 2.0562. Min Act: -0.1700
Data Index: 4722053 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0730. Min Range: -2.0730
Max Act: 2.0225. Min Act: -0.1698
Data Index: 845259 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0730. Min Range: -2.0730
Max Act: 2.0056. Min Act: -0.1699
Data Index: 7494887 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0730. Min Range: -2.0730
Max Act: 2.0056. Min Act: -0.1700
Data Index: 3268538 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0730. Min Range: -2.0730
Max Act: 2.0056. Min Act: -0.1691
Data Index: 4098860 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9887. Min Act: -0.1693
Data Index: 6674188 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9887. Min Act: -0.1698
Data Index: 5774786 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9887. Min Act: -0.1700
Data Index: 2101979 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9548. Min Act: -0.1695
Data Index: 3995193 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9718. Min Act: -0.1700
Data Index: 2162896 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9718. Min Act: -0.1700
Data Index: 5527321 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9718. Min Act: -0.1700
Data Index: 3472204 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9718. Min Act: -0.1700
Data Index: 6003349 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9718. Min Act: -0.1681
Data Index: 6187772 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9718. Min Act: -0.1700
Data Index: 6383274 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9548. Min Act: -0.1700
Data Index: 3268736 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9718. Min Act: -0.1700
Data Index: 8787778 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0730. Min Range: -2.0730
Max Act: 1.9718. Min Act: -0.1700
Data Index: 434103 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19