Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4320 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1510. Min Range: -5.1510
Max Act: 5.1510. Min Act: -0.1700
Data Index: 8098358 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1510. Min Range: -5.1510
Max Act: 5.1197. Min Act: -0.1700
Data Index: 1692016 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.9010. Min Act: -0.1700
Data Index: 2637906 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.8697. Min Act: -0.1700
Data Index: 7172814 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.8072. Min Act: -0.1700
Data Index: 7791302 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.8072. Min Act: -0.1700
Data Index: 5703510 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.8072. Min Act: -0.1700
Data Index: 7054088 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.8072. Min Act: -0.1700
Data Index: 8093704 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.8072. Min Act: -0.1700
Data Index: 45492 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.7760. Min Act: -0.1700
Data Index: 4661437 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.7447. Min Act: -0.1700
Data Index: 7791303 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.7760. Min Act: -0.1700
Data Index: 7735429 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.7447. Min Act: -0.1700
Data Index: 3209591 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.7135. Min Act: -0.1700
Data Index: 4152075 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.7135. Min Act: -0.1700
Data Index: 2785678 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.7135. Min Act: -0.1700
Data Index: 7583957 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.7135. Min Act: -0.1700
Data Index: 2293796 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.6822. Min Act: -0.1700
Data Index: 47089 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.6822. Min Act: -0.1700
Data Index: 7777638 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1510. Min Range: -5.1510
Max Act: 4.6822. Min Act: -0.1700
Data Index: 4861226 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19