Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3883 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.1821. Min Act: -0.1700
Data Index: 1139376 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.1664. Min Act: -0.1700
Data Index: 5073025 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.1349. Min Act: -0.1700
Data Index: 6787693 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.1349. Min Act: -0.1700
Data Index: 5709144 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.1349. Min Act: -0.1700
Data Index: 2190218 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.1191. Min Act: -0.1700
Data Index: 4152054 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.1191. Min Act: -0.1700
Data Index: 6782681 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.1034. Min Act: -0.1700
Data Index: 346464 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.1034. Min Act: -0.1700
Data Index: 4641117 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0876. Min Act: -0.1700
Data Index: 3822658 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0876. Min Act: -0.1700
Data Index: 6195122 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0876. Min Act: -0.1700
Data Index: 5759374 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0876. Min Act: -0.1700
Data Index: 7750205 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0876. Min Act: -0.1700
Data Index: 2021802 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0876. Min Act: -0.1700
Data Index: 137936 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0876. Min Act: -0.1700
Data Index: 2824147 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0718. Min Act: -0.1700
Data Index: 2869464 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0718. Min Act: -0.1700
Data Index: 5526512 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0718. Min Act: -0.1700
Data Index: 6155669 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1821. Min Range: -3.1821
Max Act: 3.0718. Min Act: -0.1700
Data Index: 4382268 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19