Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 92 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.4968. Min Act: -0.1700
Data Index: 5902122 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.4030. Min Act: -0.1700
Data Index: 6303773 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.3405. Min Act: -0.1700
Data Index: 2128131 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.3093. Min Act: -0.1700
Data Index: 6999851 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.2780. Min Act: -0.1700
Data Index: 1285550 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.2780. Min Act: -0.1700
Data Index: 3397470 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.2468. Min Act: -0.1700
Data Index: 2460885 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.2468. Min Act: -0.1700
Data Index: 6014357 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.1843. Min Act: -0.1700
Data Index: 2075207 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.1530. Min Act: -0.1700
Data Index: 5359833 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.1218. Min Act: -0.1700
Data Index: 2096277 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.0905. Min Act: -0.1700
Data Index: 4424529 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4968. Min Range: -5.4968
Max Act: 5.0593. Min Act: -0.1700
Data Index: 463159 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4968. Min Range: -5.4968
Max Act: 4.9968. Min Act: -0.1700
Data Index: 3750132 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4968. Min Range: -5.4968
Max Act: 4.9655. Min Act: -0.1700
Data Index: 881503 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4968. Min Range: -5.4968
Max Act: 4.9343. Min Act: -0.1700
Data Index: 6921836 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4968. Min Range: -5.4968
Max Act: 4.9343. Min Act: -0.1700
Data Index: 1926016 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4968. Min Range: -5.4968
Max Act: 4.9343. Min Act: -0.1700
Data Index: 6014358 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4968. Min Range: -5.4968
Max Act: 4.9030. Min Act: -0.1700
Data Index: 1070623 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4968. Min Range: -5.4968
Max Act: 4.9030. Min Act: -0.1700
Data Index: 808183 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19