Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.7954. Min Act: -0.1700
Data Index: 5679164 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.2016. Min Act: -0.1700
Data Index: 1432977 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.0766. Min Act: -0.1700
Data Index: 974281 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.0454. Min Act: -0.1700
Data Index: 1766829 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.0454. Min Act: -0.1700
Data Index: 7608008 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.0454. Min Act: -0.1700
Data Index: 1766824 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.9516. Min Act: -0.1700
Data Index: 1809783 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7954. Min Range: -7.7954
Max Act: 7.0141. Min Act: -0.1700
Data Index: 1238872 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.8891. Min Act: -0.1700
Data Index: 133284 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.8891. Min Act: -0.1700
Data Index: 4351341 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.8891. Min Act: -0.1700
Data Index: 8256915 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.8891. Min Act: -0.1700
Data Index: 7509277 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.8891. Min Act: -0.1700
Data Index: 5778323 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.8891. Min Act: -0.1700
Data Index: 8797670 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.8266. Min Act: -0.1700
Data Index: 1766831 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.7954. Min Act: -0.1700
Data Index: 5240459 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.8266. Min Act: -0.1700
Data Index: 8256922 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.7641. Min Act: -0.1700
Data Index: 7002880 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.7641. Min Act: -0.1700
Data Index: 8256930 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7954. Min Range: -7.7954
Max Act: 6.7954. Min Act: -0.1700
Data Index: 5775835 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19