Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3262 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1545. Min Range: -5.1545
Max Act: 5.1545. Min Act: -0.1700
Data Index: 1196116 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1545. Min Range: -5.1545
Max Act: 5.0920. Min Act: -0.1700
Data Index: 2171212 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1545. Min Range: -5.1545
Max Act: 5.0295. Min Act: -0.1700
Data Index: 1481310 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.9670. Min Act: -0.1700
Data Index: 6333214 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.9358. Min Act: -0.1700
Data Index: 4166834 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.9045. Min Act: -0.1700
Data Index: 2786523 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.9045. Min Act: -0.1700
Data Index: 8100932 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.8733. Min Act: -0.1700
Data Index: 6964243 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.8733. Min Act: -0.1700
Data Index: 4854933 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.9045. Min Act: -0.1700
Data Index: 5596340 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.8420. Min Act: -0.1700
Data Index: 186277 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.8420. Min Act: -0.1700
Data Index: 8038859 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.8420. Min Act: -0.1700
Data Index: 315348 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.8420. Min Act: -0.1700
Data Index: 1178078 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.8108. Min Act: -0.1700
Data Index: 1765754 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.8108. Min Act: -0.1700
Data Index: 3661949 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.8108. Min Act: -0.1700
Data Index: 6851095 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.8108. Min Act: -0.1700
Data Index: 7298679 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.7483. Min Act: -0.1700
Data Index: 6310716 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1545. Min Range: -5.1545
Max Act: 4.7795. Min Act: -0.1700
Data Index: 5546718 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19