Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 62 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.5641. Min Act: -0.1700
Data Index: 5794238 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.4078. Min Act: -0.1700
Data Index: 6829612 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5641. Min Range: -5.5641
Max Act: 5.0016. Min Act: -0.1700
Data Index: 168317 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.9391. Min Act: -0.1700
Data Index: 604307 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.9391. Min Act: -0.1700
Data Index: 4913890 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.8453. Min Act: -0.1700
Data Index: 4025528 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.8141. Min Act: -0.1700
Data Index: 5361923 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.8141. Min Act: -0.1700
Data Index: 5068728 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7516. Min Act: -0.1700
Data Index: 1967815 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7828. Min Act: -0.1700
Data Index: 2624781 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7516. Min Act: -0.1700
Data Index: 2266289 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7516. Min Act: -0.1700
Data Index: 2582542 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7516. Min Act: -0.1700
Data Index: 3560113 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7203. Min Act: -0.1700
Data Index: 5132484 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7203. Min Act: -0.1700
Data Index: 1222678 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7203. Min Act: -0.1700
Data Index: 2102236 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7203. Min Act: -0.1700
Data Index: 2624795 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.6891. Min Act: -0.1700
Data Index: 6324793 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7203. Min Act: -0.1700
Data Index: 4644587 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5641. Min Range: -5.5641
Max Act: 4.7203. Min Act: -0.1700
Data Index: 4739253 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19