Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5679 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.6725. Min Act: -0.1700
Data Index: 4807829 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.2350. Min Act: -0.1700
Data Index: 8583729 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.2350. Min Act: -0.1700
Data Index: 6616969 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.2038. Min Act: -0.1700
Data Index: 6049866 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.2038. Min Act: -0.1700
Data Index: 3877337 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.1725. Min Act: -0.1700
Data Index: 1813072 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.2038. Min Act: -0.1700
Data Index: 69377 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.1413. Min Act: -0.1700
Data Index: 1544542 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.1100. Min Act: -0.1700
Data Index: 4422899 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.1100. Min Act: -0.1700
Data Index: 6187172 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.0788. Min Act: -0.1700
Data Index: 5390066 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.0475. Min Act: -0.1700
Data Index: 4140070 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.0475. Min Act: -0.1700
Data Index: 1875159 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.0475. Min Act: -0.1700
Data Index: 5764998 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.0475. Min Act: -0.1700
Data Index: 2420215 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.0475. Min Act: -0.1700
Data Index: 653314 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6725. Min Range: -7.6725
Max Act: 7.0163. Min Act: -0.1700
Data Index: 7029681 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6725. Min Range: -7.6725
Max Act: 6.9850. Min Act: -0.1700
Data Index: 7559410 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6725. Min Range: -7.6725
Max Act: 6.9538. Min Act: -0.1700
Data Index: 5269832 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6725. Min Range: -7.6725
Max Act: 6.9850. Min Act: -0.1700
Data Index: 5530161 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19