Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 995 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.9195. Min Act: -0.1700
Data Index: 2013279 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.7945. Min Act: -0.1700
Data Index: 1304993 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.7632. Min Act: -0.1700
Data Index: 4849142 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.7320. Min Act: -0.1700
Data Index: 1789229 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.6382. Min Act: -0.1700
Data Index: 5004950 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.6382. Min Act: -0.1700
Data Index: 8680614 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.6382. Min Act: -0.1700
Data Index: 2391060 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.6070. Min Act: -0.1700
Data Index: 8236101 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.6070. Min Act: -0.1700
Data Index: 987464 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.5757. Min Act: -0.1700
Data Index: 36934 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.5757. Min Act: -0.1700
Data Index: 5335326 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.5757. Min Act: -0.1700
Data Index: 1228910 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.5757. Min Act: -0.1700
Data Index: 5097306 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.5757. Min Act: -0.1700
Data Index: 6741680 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.6070. Min Act: -0.1700
Data Index: 2282489 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.5132. Min Act: -0.1700
Data Index: 4131030 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.5445. Min Act: -0.1700
Data Index: 7494570 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.5132. Min Act: -0.1700
Data Index: 8495557 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.5757. Min Act: -0.1700
Data Index: 263316 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9195. Min Range: -4.9195
Max Act: 4.5757. Min Act: -0.1700
Data Index: 4878716 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19