Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3761 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.4888. Min Act: -0.1700
Data Index: 6446560 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.9576. Min Act: -0.1700
Data Index: 4423354 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.9576. Min Act: -0.1700
Data Index: 6695576 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.8951. Min Act: -0.1700
Data Index: 6695591 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.8951. Min Act: -0.1700
Data Index: 4694000 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.8951. Min Act: -0.1700
Data Index: 7139021 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.8326. Min Act: -0.1700
Data Index: 7838720 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.7076. Min Act: -0.1700
Data Index: 5420087 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.7076. Min Act: -0.1700
Data Index: 8043950 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.6451. Min Act: -0.1700
Data Index: 447026 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.5826. Min Act: -0.1700
Data Index: 8017760 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.5826. Min Act: -0.1700
Data Index: 978088 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.5513. Min Act: -0.1700
Data Index: 869461 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.5513. Min Act: -0.1700
Data Index: 4442141 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.5513. Min Act: -0.1700
Data Index: 5164390 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.4576. Min Act: -0.1700
Data Index: 7068105 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.4576. Min Act: -0.1700
Data Index: 5040252 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.4576. Min Act: -0.1700
Data Index: 5164391 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.3326. Min Act: -0.1700
Data Index: 3244548 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4888. Min Range: -8.4888
Max Act: 7.3326. Min Act: -0.1700
Data Index: 7535800 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19