Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4436 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1958. Min Range: -8.1958
Max Act: 8.1958. Min Act: -0.1700
Data Index: 7857114 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1958. Min Range: -8.1958
Max Act: 8.0083. Min Act: -0.1700
Data Index: 5472018 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1958. Min Range: -8.1958
Max Act: 8.0083. Min Act: -0.1700
Data Index: 6695112 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1958. Min Range: -8.1958
Max Act: 8.0083. Min Act: -0.1700
Data Index: 8104963 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.9458. Min Act: -0.1700
Data Index: 6669739 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.9458. Min Act: -0.1700
Data Index: 3422194 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.8208. Min Act: -0.1700
Data Index: 5738145 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.8208. Min Act: -0.1700
Data Index: 6291044 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.8208. Min Act: -0.1700
Data Index: 5892331 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.8208. Min Act: -0.1700
Data Index: 958385 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.8208. Min Act: -0.1700
Data Index: 2834400 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.7895. Min Act: -0.1700
Data Index: 2569921 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.6645. Min Act: -0.1700
Data Index: 2367018 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.6645. Min Act: -0.1700
Data Index: 912164 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.6333. Min Act: -0.1700
Data Index: 5556888 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.6020. Min Act: -0.1700
Data Index: 8767876 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.6020. Min Act: -0.1700
Data Index: 1117882 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.5708. Min Act: -0.1700
Data Index: 4804831 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.6020. Min Act: -0.1700
Data Index: 1126191 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1958. Min Range: -8.1958
Max Act: 7.5708. Min Act: -0.1700
Data Index: 4959714 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19