Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 821 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0884. Min Range: -7.0884
Max Act: 7.0884. Min Act: -0.1700
Data Index: 6819274 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.9634. Min Act: -0.1700
Data Index: 7898748 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.8697. Min Act: -0.1700
Data Index: 6846862 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.8697. Min Act: -0.1700
Data Index: 140425 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.8384. Min Act: -0.1700
Data Index: 8183284 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.7447. Min Act: -0.1700
Data Index: 7701221 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.7134. Min Act: -0.1700
Data Index: 6368842 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.7134. Min Act: -0.1700
Data Index: 3214698 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.6509. Min Act: -0.1700
Data Index: 1839457 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.6509. Min Act: -0.1700
Data Index: 2565339 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.6197. Min Act: -0.1700
Data Index: 5890731 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.5884. Min Act: -0.1700
Data Index: 1857601 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.5884. Min Act: -0.1700
Data Index: 5592575 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.5884. Min Act: -0.1700
Data Index: 8672870 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.5884. Min Act: -0.1700
Data Index: 1430592 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.5259. Min Act: -0.1700
Data Index: 8305562 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.5259. Min Act: -0.1700
Data Index: 367788 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.5259. Min Act: -0.1700
Data Index: 5890730 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.4947. Min Act: -0.1700
Data Index: 1893667 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0884. Min Range: -7.0884
Max Act: 6.4634. Min Act: -0.1700
Data Index: 7230474 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19