Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3050 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0244. Min Range: -3.0244
Max Act: 3.0244. Min Act: -0.1700
Data Index: 8312970 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9928. Min Act: -0.1700
Data Index: 4348940 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0244. Min Range: -3.0244
Max Act: 3.0086. Min Act: -0.1700
Data Index: 7746931 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9612. Min Act: -0.1700
Data Index: 7313897 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9770. Min Act: -0.1700
Data Index: 6750862 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9770. Min Act: -0.1700
Data Index: 2635294 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9770. Min Act: -0.1700
Data Index: 6834512 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9612. Min Act: -0.1700
Data Index: 177718 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9295. Min Act: -0.1700
Data Index: 2733162 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9770. Min Act: -0.1700
Data Index: 7461894 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9454. Min Act: -0.1700
Data Index: 7068076 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9454. Min Act: -0.1700
Data Index: 6597398 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9295. Min Act: -0.1700
Data Index: 6664234 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.9137. Min Act: -0.1700
Data Index: 7299214 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.8978. Min Act: -0.1700
Data Index: 6056677 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.8820. Min Act: -0.1700
Data Index: 8130985 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.8820. Min Act: -0.1700
Data Index: 6382687 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.8820. Min Act: -0.1700
Data Index: 1115033 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.8661. Min Act: -0.1700
Data Index: 1074989 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0244. Min Range: -3.0244
Max Act: 2.8502. Min Act: -0.1700
Data Index: 3397480 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19