Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.3030. Min Act: -0.1700
Data Index: 3570317 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.2718. Min Act: -0.1700
Data Index: 8437416 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.2405. Min Act: -0.1700
Data Index: 4178163 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.2093. Min Act: -0.1700
Data Index: 6343233 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.1468. Min Act: -0.1700
Data Index: 4047292 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.0843. Min Act: -0.1700
Data Index: 3565148 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.0843. Min Act: -0.1700
Data Index: 4832553 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.0530. Min Act: -0.1700
Data Index: 3288000 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.0530. Min Act: -0.1700
Data Index: 2603093 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.0218. Min Act: -0.1700
Data Index: 2407523 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.0218. Min Act: -0.1700
Data Index: 1691273 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.0218. Min Act: -0.1700
Data Index: 5459049 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.0218. Min Act: -0.1700
Data Index: 239952 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3030. Min Range: -5.3030
Max Act: 4.9905. Min Act: -0.1700
Data Index: 8236279 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3030. Min Range: -5.3030
Max Act: 4.9905. Min Act: -0.1700
Data Index: 8012382 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3030. Min Range: -5.3030
Max Act: 4.9905. Min Act: -0.1700
Data Index: 4832554 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3030. Min Range: -5.3030
Max Act: 5.0218. Min Act: -0.1700
Data Index: 3614092 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3030. Min Range: -5.3030
Max Act: 4.9905. Min Act: -0.1700
Data Index: 7448888 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3030. Min Range: -5.3030
Max Act: 4.9593. Min Act: -0.1700
Data Index: 5700193 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3030. Min Range: -5.3030
Max Act: 4.9593. Min Act: -0.1700
Data Index: 3489785 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19