Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 43 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.6536. Min Act: -0.1700
Data Index: 8582508 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.6536. Min Act: -0.1700
Data Index: 3866711 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.5911. Min Act: -0.1700
Data Index: 3086776 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.4348. Min Act: -0.1700
Data Index: 3227924 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.4036. Min Act: -0.1700
Data Index: 3696580 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.4036. Min Act: -0.1700
Data Index: 6646928 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.3098. Min Act: -0.1700
Data Index: 3154702 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.1848. Min Act: -0.1700
Data Index: 5949214 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.1223. Min Act: -0.1700
Data Index: 7922611 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.1223. Min Act: -0.1700
Data Index: 7157052 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.1223. Min Act: -0.1700
Data Index: 4837929 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.0911. Min Act: -0.1700
Data Index: 6322493 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.0911. Min Act: -0.1700
Data Index: 6787284 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.0911. Min Act: -0.1700
Data Index: 4297876 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6536. Min Range: -7.6536
Max Act: 7.0598. Min Act: -0.1700
Data Index: 593207 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6536. Min Range: -7.6536
Max Act: 6.9973. Min Act: -0.1700
Data Index: 7489965 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6536. Min Range: -7.6536
Max Act: 6.9973. Min Act: -0.1700
Data Index: 1247158 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6536. Min Range: -7.6536
Max Act: 6.9973. Min Act: -0.1700
Data Index: 5676524 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6536. Min Range: -7.6536
Max Act: 6.9973. Min Act: -0.1700
Data Index: 8039771 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6536. Min Range: -7.6536
Max Act: 6.9661. Min Act: -0.1700
Data Index: 5415602 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19