Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 890 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.7305. Min Act: -0.1700
Data Index: 5628642 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.6993. Min Act: -0.1700
Data Index: 5567502 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.6055. Min Act: -0.1700
Data Index: 8716294 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.5743. Min Act: -0.1700
Data Index: 6651666 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.4493. Min Act: -0.1700
Data Index: 7139918 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.4180. Min Act: -0.1700
Data Index: 8296861 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.4493. Min Act: -0.1700
Data Index: 2446145 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.3555. Min Act: -0.1700
Data Index: 8165614 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.3243. Min Act: -0.1700
Data Index: 7171059 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.2930. Min Act: -0.1700
Data Index: 1486454 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.2930. Min Act: -0.1700
Data Index: 2796828 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.3243. Min Act: -0.1700
Data Index: 4210861 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.2618. Min Act: -0.1700
Data Index: 1748179 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.2930. Min Act: -0.1700
Data Index: 7977983 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.2618. Min Act: -0.1700
Data Index: 7578203 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.2305. Min Act: -0.1700
Data Index: 3787274 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.2618. Min Act: -0.1700
Data Index: 4112314 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.1680. Min Act: -0.1700
Data Index: 5224806 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.1993. Min Act: -0.1700
Data Index: 2334905 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7305. Min Range: -5.7305
Max Act: 5.1993. Min Act: -0.1700
Data Index: 6001488 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19