Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0260. Min Range: -4.0260
Max Act: 4.0260. Min Act: -0.1700
Data Index: 6792587 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.9635. Min Act: -0.1700
Data Index: 1321035 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.9948. Min Act: -0.1700
Data Index: 7734703 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.9322. Min Act: -0.1700
Data Index: 8074339 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.9010. Min Act: -0.1700
Data Index: 5515224 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.9010. Min Act: -0.1700
Data Index: 4636528 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.8697. Min Act: -0.1700
Data Index: 5024919 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.8697. Min Act: -0.1700
Data Index: 7142017 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.8697. Min Act: -0.1700
Data Index: 4175460 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.8697. Min Act: -0.1700
Data Index: 5198516 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.8697. Min Act: -0.1700
Data Index: 4062460 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.8697. Min Act: -0.1700
Data Index: 5261721 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.8384. Min Act: -0.1700
Data Index: 7696600 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.8072. Min Act: -0.1700
Data Index: 2625926 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.7759. Min Act: -0.1700
Data Index: 7113695 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.7759. Min Act: -0.1700
Data Index: 5475306 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.7759. Min Act: -0.1700
Data Index: 6981907 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.7446. Min Act: -0.1700
Data Index: 3126 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.7759. Min Act: -0.1700
Data Index: 6713738 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0260. Min Range: -4.0260
Max Act: 3.7759. Min Act: -0.1700
Data Index: 8539842 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19