Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4280 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.2900. Min Act: -0.1700
Data Index: 2540664 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.1327. Min Act: -0.1700
Data Index: 2780179 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.1170. Min Act: -0.1700
Data Index: 75402 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.1170. Min Act: -0.1700
Data Index: 6625756 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.1012. Min Act: -0.1700
Data Index: 6789860 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0854. Min Act: -0.1700
Data Index: 5895770 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.1012. Min Act: -0.1700
Data Index: 7914141 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0539. Min Act: -0.1700
Data Index: 5941393 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0381. Min Act: -0.1700
Data Index: 3227220 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0381. Min Act: -0.1700
Data Index: 5574115 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0223. Min Act: -0.1700
Data Index: 1156049 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0381. Min Act: -0.1700
Data Index: 298588 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0381. Min Act: -0.1700
Data Index: 4235164 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0381. Min Act: -0.1700
Data Index: 5075678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0065. Min Act: -0.1700
Data Index: 5526209 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0065. Min Act: -0.1700
Data Index: 2712285 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2900. Min Range: -3.2900
Max Act: 2.9749. Min Act: -0.1700
Data Index: 3056693 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2900. Min Range: -3.2900
Max Act: 2.9907. Min Act: -0.1700
Data Index: 5645887 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2900. Min Range: -3.2900
Max Act: 3.0065. Min Act: -0.1700
Data Index: 3692289 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2900. Min Range: -3.2900
Max Act: 2.9907. Min Act: -0.1700
Data Index: 6472256 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19