Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1038 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1692. Min Range: -5.1692
Max Act: 5.1692. Min Act: -0.1700
Data Index: 7918864 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1692. Min Range: -5.1692
Max Act: 5.1067. Min Act: -0.1700
Data Index: 5690852 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.9817. Min Act: -0.1700
Data Index: 6840961 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1692. Min Range: -5.1692
Max Act: 5.0129. Min Act: -0.1700
Data Index: 6231661 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.9817. Min Act: -0.1700
Data Index: 4482436 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.9504. Min Act: -0.1700
Data Index: 5062596 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.9504. Min Act: -0.1700
Data Index: 810175 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.9504. Min Act: -0.1700
Data Index: 3346909 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.9192. Min Act: -0.1700
Data Index: 7280181 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.8879. Min Act: -0.1700
Data Index: 3080116 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.8879. Min Act: -0.1700
Data Index: 4617617 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.8879. Min Act: -0.1700
Data Index: 6627799 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.8879. Min Act: -0.1700
Data Index: 7660253 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.8879. Min Act: -0.1700
Data Index: 5989848 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.8879. Min Act: -0.1700
Data Index: 4476459 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.9192. Min Act: -0.1700
Data Index: 4146307 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.8879. Min Act: -0.1700
Data Index: 1884887 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.8567. Min Act: -0.1700
Data Index: 1309412 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.8567. Min Act: -0.1700
Data Index: 5195379 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1692. Min Range: -5.1692
Max Act: 4.7942. Min Act: -0.1700
Data Index: 6807878 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19