Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 582 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.8549. Min Act: -0.1700
Data Index: 2181760 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.7924. Min Act: -0.1700
Data Index: 914144 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.7299. Min Act: -0.1700
Data Index: 2119459 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.7299. Min Act: -0.1700
Data Index: 6224871 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.7299. Min Act: -0.1700
Data Index: 4963372 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.6049. Min Act: -0.1700
Data Index: 6065261 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.5737. Min Act: -0.1700
Data Index: 2163588 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.5424. Min Act: -0.1700
Data Index: 2311285 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.5424. Min Act: -0.1700
Data Index: 5990138 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.5424. Min Act: -0.1700
Data Index: 8005381 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.5112. Min Act: -0.1700
Data Index: 6593443 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.5112. Min Act: -0.1700
Data Index: 8089209 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.5112. Min Act: -0.1700
Data Index: 8345169 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.4799. Min Act: -0.1700
Data Index: 1333359 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.4799. Min Act: -0.1700
Data Index: 8265780 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.4799. Min Act: -0.1700
Data Index: 2366283 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.4487. Min Act: -0.1700
Data Index: 1049126 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.4174. Min Act: -0.1700
Data Index: 5037145 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.4174. Min Act: -0.1700
Data Index: 2367831 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8549. Min Range: -6.8549
Max Act: 6.3549. Min Act: -0.1700
Data Index: 116897 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19