Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.3125. Min Act: -0.1700
Data Index: 7652660 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.2500. Min Act: -0.1700
Data Index: 8656135 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.2187. Min Act: -0.1700
Data Index: 7488403 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.2187. Min Act: -0.1700
Data Index: 8197707 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.1875. Min Act: -0.1700
Data Index: 3016960 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.1875. Min Act: -0.1700
Data Index: 4385593 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.1875. Min Act: -0.1700
Data Index: 1709025 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.1250. Min Act: -0.1700
Data Index: 7406331 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.1250. Min Act: -0.1700
Data Index: 4385595 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.1562. Min Act: -0.1700
Data Index: 6752565 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.0625. Min Act: -0.1700
Data Index: 4140896 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.0625. Min Act: -0.1700
Data Index: 8405586 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.0625. Min Act: -0.1700
Data Index: 6118574 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.0000. Min Act: -0.1700
Data Index: 73913 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.0000. Min Act: -0.1700
Data Index: 4871013 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.0000. Min Act: -0.1700
Data Index: 3655976 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.0000. Min Act: -0.1700
Data Index: 1666064 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.0000. Min Act: -0.1700
Data Index: 1817275 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3125. Min Range: -6.3125
Max Act: 6.0000. Min Act: -0.1700
Data Index: 2719938 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3125. Min Range: -6.3125
Max Act: 5.9687. Min Act: -0.1700
Data Index: 7339939 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19