Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2135 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2046. Min Range: -8.2046
Max Act: 8.2046. Min Act: -0.1700
Data Index: 5121594 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.9546. Min Act: -0.1700
Data Index: 572371 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.9546. Min Act: -0.1700
Data Index: 420987 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.8296. Min Act: -0.1700
Data Index: 107717 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.7671. Min Act: -0.1700
Data Index: 6526653 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.7671. Min Act: -0.1700
Data Index: 5283390 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.7046. Min Act: -0.1700
Data Index: 6790395 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.7671. Min Act: -0.1700
Data Index: 2995875 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.7046. Min Act: -0.1700
Data Index: 5858550 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.7046. Min Act: -0.1700
Data Index: 7298803 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.6421. Min Act: -0.1700
Data Index: 6743627 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.6109. Min Act: -0.1700
Data Index: 4470097 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.6109. Min Act: -0.1700
Data Index: 305139 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.5796. Min Act: -0.1700
Data Index: 6589339 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.5484. Min Act: -0.1700
Data Index: 1429437 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.5171. Min Act: -0.1700
Data Index: 7961865 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.5171. Min Act: -0.1700
Data Index: 2221855 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.5484. Min Act: -0.1700
Data Index: 3429626 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.4859. Min Act: -0.1700
Data Index: 4810589 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2046. Min Range: -8.2046
Max Act: 7.4859. Min Act: -0.1700
Data Index: 7100631 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19