Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.8131. Min Act: -0.1700
Data Index: 6343396 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.7506. Min Act: -0.1700
Data Index: 735782 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.6881. Min Act: -0.1700
Data Index: 4185749 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.6881. Min Act: -0.1700
Data Index: 6343402 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.6881. Min Act: -0.1700
Data Index: 2713685 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.5943. Min Act: -0.1700
Data Index: 6417253 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.5943. Min Act: -0.1700
Data Index: 1748484 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.5318. Min Act: -0.1700
Data Index: 5047174 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.5006. Min Act: -0.1700
Data Index: 3329471 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.5006. Min Act: -0.1700
Data Index: 8357821 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.4693. Min Act: -0.1700
Data Index: 8519465 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.4381. Min Act: -0.1700
Data Index: 6782334 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.4381. Min Act: -0.1700
Data Index: 6294550 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.3756. Min Act: -0.1700
Data Index: 3983000 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.3443. Min Act: -0.1700
Data Index: 2400876 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.4068. Min Act: -0.1700
Data Index: 602060 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.3443. Min Act: -0.1700
Data Index: 914020 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.3443. Min Act: -0.1700
Data Index: 1748924 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.3756. Min Act: -0.1700
Data Index: 5369255 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8131. Min Range: -6.8131
Max Act: 6.3131. Min Act: -0.1700
Data Index: 3107057 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19