Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2678 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.6510. Min Act: -0.1700
Data Index: 3012023 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.5885. Min Act: -0.1700
Data Index: 620550 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.6198. Min Act: -0.1700
Data Index: 6731497 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.5573. Min Act: -0.1700
Data Index: 4074841 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.5260. Min Act: -0.1700
Data Index: 6147882 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.4635. Min Act: -0.1700
Data Index: 3397199 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.4635. Min Act: -0.1700
Data Index: 3454416 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.4635. Min Act: -0.1700
Data Index: 8804668 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.4010. Min Act: -0.1700
Data Index: 3648600 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.4010. Min Act: -0.1700
Data Index: 993042 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.3385. Min Act: -0.1700
Data Index: 8218560 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.3385. Min Act: -0.1700
Data Index: 5490855 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.3385. Min Act: -0.1700
Data Index: 6897086 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.3385. Min Act: -0.1700
Data Index: 2339249 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.3073. Min Act: -0.1700
Data Index: 6635936 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.3385. Min Act: -0.1700
Data Index: 7607256 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.3073. Min Act: -0.1700
Data Index: 7511482 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.2760. Min Act: -0.1700
Data Index: 2820568 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.2760. Min Act: -0.1700
Data Index: 980389 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6510. Min Range: -4.6510
Max Act: 4.2760. Min Act: -0.1700
Data Index: 7431735 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19