Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.9271. Min Act: -0.1700
Data Index: 8668790 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.8646. Min Act: -0.1700
Data Index: 8812514 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.8334. Min Act: -0.1700
Data Index: 2160666 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.8334. Min Act: -0.1700
Data Index: 6990777 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.8334. Min Act: -0.1700
Data Index: 733379 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.8021. Min Act: -0.1700
Data Index: 1380549 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.7396. Min Act: -0.1700
Data Index: 5300597 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.7709. Min Act: -0.1700
Data Index: 5372309 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.7709. Min Act: -0.1700
Data Index: 344999 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.8021. Min Act: -0.1700
Data Index: 3338195 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.7084. Min Act: -0.1700
Data Index: 6076655 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.7084. Min Act: -0.1700
Data Index: 8812518 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6771. Min Act: -0.1700
Data Index: 4308395 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6771. Min Act: -0.1700
Data Index: 1211976 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6459. Min Act: -0.1700
Data Index: 2983538 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6771. Min Act: -0.1700
Data Index: 740648 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6771. Min Act: -0.1700
Data Index: 6205813 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6771. Min Act: -0.1700
Data Index: 1215128 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6771. Min Act: -0.1700
Data Index: 4702957 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9271. Min Range: -5.9271
Max Act: 5.6146. Min Act: -0.1700
Data Index: 5197396 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19