Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1172 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.5362. Min Act: -0.1700
Data Index: 6140367 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.1925. Min Act: -0.1700
Data Index: 4854317 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.1612. Min Act: -0.1700
Data Index: 1898627 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.1300. Min Act: -0.1700
Data Index: 7604275 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.0987. Min Act: -0.1700
Data Index: 7542347 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.0362. Min Act: -0.1700
Data Index: 8702761 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.0050. Min Act: -0.1700
Data Index: 1279375 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.0050. Min Act: -0.1700
Data Index: 4646672 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.0050. Min Act: -0.1700
Data Index: 43429 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.0050. Min Act: -0.1700
Data Index: 5774763 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5362. Min Range: -5.5362
Max Act: 5.0050. Min Act: -0.1700
Data Index: 4700124 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5362. Min Range: -5.5362
Max Act: 4.9425. Min Act: -0.1700
Data Index: 4211910 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5362. Min Range: -5.5362
Max Act: 4.9737. Min Act: -0.1700
Data Index: 6621464 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5362. Min Range: -5.5362
Max Act: 4.9737. Min Act: -0.1700
Data Index: 6375271 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5362. Min Range: -5.5362
Max Act: 4.9737. Min Act: -0.1700
Data Index: 7675865 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5362. Min Range: -5.5362
Max Act: 4.9737. Min Act: -0.1700
Data Index: 518908 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5362. Min Range: -5.5362
Max Act: 4.9737. Min Act: -0.1700
Data Index: 2943619 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5362. Min Range: -5.5362
Max Act: 4.9425. Min Act: -0.1700
Data Index: 765743 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5362. Min Range: -5.5362
Max Act: 4.9425. Min Act: -0.1700
Data Index: 4280703 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5362. Min Range: -5.5362
Max Act: 4.9425. Min Act: -0.1700
Data Index: 1216963 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19