Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 365 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5780. Min Range: -7.5780
Max Act: 7.5780. Min Act: -0.1700
Data Index: 4948071 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5780. Min Range: -7.5780
Max Act: 7.4218. Min Act: -0.1700
Data Index: 2636443 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5780. Min Range: -7.5780
Max Act: 7.2655. Min Act: -0.1700
Data Index: 1004387 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5780. Min Range: -7.5780
Max Act: 7.1718. Min Act: -0.1700
Data Index: 4856426 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5780. Min Range: -7.5780
Max Act: 7.1718. Min Act: -0.1700
Data Index: 1501476 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5780. Min Range: -7.5780
Max Act: 7.1093. Min Act: -0.1700
Data Index: 3510550 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5780. Min Range: -7.5780
Max Act: 7.0780. Min Act: -0.1700
Data Index: 2791761 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5780. Min Range: -7.5780
Max Act: 7.0468. Min Act: -0.1700
Data Index: 6832451 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5780. Min Range: -7.5780
Max Act: 7.0155. Min Act: -0.1700
Data Index: 5784402 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.9218. Min Act: -0.1700
Data Index: 4454171 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.9218. Min Act: -0.1700
Data Index: 1154680 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.8593. Min Act: -0.1700
Data Index: 4993003 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.8593. Min Act: -0.1700
Data Index: 5428120 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.8280. Min Act: -0.1700
Data Index: 829134 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.8280. Min Act: -0.1700
Data Index: 341164 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.8280. Min Act: -0.1700
Data Index: 6680738 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.7655. Min Act: -0.1700
Data Index: 1029969 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.7343. Min Act: -0.1700
Data Index: 522641 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.7343. Min Act: -0.1700
Data Index: 7927319 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5780. Min Range: -7.5780
Max Act: 6.7343. Min Act: -0.1700
Data Index: 5328059 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19