Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.2282. Min Act: -0.1700
Data Index: 4422109 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.1970. Min Act: -0.1699
Data Index: 7131705 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.1657. Min Act: -0.1700
Data Index: 5606963 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.1345. Min Act: -0.1699
Data Index: 334532 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.1345. Min Act: -0.1700
Data Index: 5459805 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.1032. Min Act: -0.1700
Data Index: 2044198 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0407. Min Act: -0.1700
Data Index: 5464491 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0720. Min Act: -0.1700
Data Index: 2044201 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0720. Min Act: -0.1700
Data Index: 588098 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0407. Min Act: -0.1697
Data Index: 1408700 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0407. Min Act: -0.1700
Data Index: 4666842 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0095. Min Act: -0.1700
Data Index: 7221898 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0407. Min Act: -0.1700
Data Index: 1403600 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0095. Min Act: -0.1700
Data Index: 8278709 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0095. Min Act: -0.1700
Data Index: 2221266 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0720. Min Act: -0.1700
Data Index: 2026098 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0095. Min Act: -0.1700
Data Index: 5598282 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2282. Min Range: -5.2282
Max Act: 5.0095. Min Act: -0.1700
Data Index: 3686745 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2282. Min Range: -5.2282
Max Act: 4.9782. Min Act: -0.1699
Data Index: 6967576 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2282. Min Range: -5.2282
Max Act: 4.9782. Min Act: -0.1700
Data Index: 5927824 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19