Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1035 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2166. Min Range: -7.2166
Max Act: 7.2166. Min Act: -0.1700
Data Index: 2646087 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2166. Min Range: -7.2166
Max Act: 7.0603. Min Act: -0.1700
Data Index: 2580291 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.9666. Min Act: -0.1700
Data Index: 2309920 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.9041. Min Act: -0.1700
Data Index: 5738680 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.9041. Min Act: -0.1700
Data Index: 5409076 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.9041. Min Act: -0.1700
Data Index: 6725694 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.8416. Min Act: -0.1700
Data Index: 5007226 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.8728. Min Act: -0.1700
Data Index: 8443190 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.8728. Min Act: -0.1700
Data Index: 4222127 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.8416. Min Act: -0.1700
Data Index: 3196954 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.8416. Min Act: -0.1700
Data Index: 4982771 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.8416. Min Act: -0.1700
Data Index: 5458045 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.8416. Min Act: -0.1700
Data Index: 6491630 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.9041. Min Act: -0.1700
Data Index: 7299829 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.7791. Min Act: -0.1700
Data Index: 3071517 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.7791. Min Act: -0.1700
Data Index: 1202945 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.8416. Min Act: -0.1700
Data Index: 2405023 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.7478. Min Act: -0.1700
Data Index: 5464769 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.7478. Min Act: -0.1700
Data Index: 7054484 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2166. Min Range: -7.2166
Max Act: 6.7791. Min Act: -0.1700
Data Index: 3068170 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19