Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.5571. Min Act: -0.1700
Data Index: 2377809 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.5259. Min Act: -0.1700
Data Index: 7077018 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.3696. Min Act: -0.1700
Data Index: 3383006 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.3696. Min Act: -0.1700
Data Index: 480479 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.3384. Min Act: -0.1700
Data Index: 3973374 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.3384. Min Act: -0.1700
Data Index: 6385673 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.2759. Min Act: -0.1700
Data Index: 7996771 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.3071. Min Act: -0.1700
Data Index: 6123525 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.3071. Min Act: -0.1700
Data Index: 879662 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.2134. Min Act: -0.1700
Data Index: 6671568 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.1821. Min Act: -0.1700
Data Index: 1919435 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.1821. Min Act: -0.1700
Data Index: 6593084 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.1821. Min Act: -0.1700
Data Index: 5895266 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.1196. Min Act: -0.1700
Data Index: 2878059 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.0884. Min Act: -0.1700
Data Index: 4869271 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.1196. Min Act: -0.1700
Data Index: 6958238 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.0259. Min Act: -0.1700
Data Index: 7751695 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.0259. Min Act: -0.1700
Data Index: 3781216 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5571. Min Range: -6.5571
Max Act: 6.0259. Min Act: -0.1700
Data Index: 6009216 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5571. Min Range: -6.5571
Max Act: 5.9946. Min Act: -0.1700
Data Index: 5860776 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19