Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5958. Min Act: -0.1700
Data Index: 2941831 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5020. Min Act: -0.1700
Data Index: 4924830 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.5020. Min Act: -0.1700
Data Index: 4314568 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.3770. Min Act: -0.1700
Data Index: 2750641 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.3770. Min Act: -0.1700
Data Index: 8589929 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.3458. Min Act: -0.1700
Data Index: 5025018 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.3145. Min Act: -0.1700
Data Index: 4511967 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.3458. Min Act: -0.1700
Data Index: 2637333 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.3145. Min Act: -0.1700
Data Index: 1426718 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.3145. Min Act: -0.1700
Data Index: 5964686 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.2833. Min Act: -0.1700
Data Index: 2604135 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.2833. Min Act: -0.1700
Data Index: 4019314 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.2520. Min Act: -0.1700
Data Index: 7248572 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.2520. Min Act: -0.1700
Data Index: 4155533 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.2833. Min Act: -0.1700
Data Index: 7210475 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.2520. Min Act: -0.1700
Data Index: 7777429 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.2520. Min Act: -0.1700
Data Index: 6108363 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.2208. Min Act: -0.1700
Data Index: 7759974 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.2208. Min Act: -0.1700
Data Index: 4067702 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5958. Min Range: -6.5958
Max Act: 6.2208. Min Act: -0.1700
Data Index: 7813351 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19