Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1700 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1937. Min Range: -6.1937
Max Act: 6.1937. Min Act: -0.1700
Data Index: 7368528 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1937. Min Range: -6.1937
Max Act: 6.0999. Min Act: -0.1700
Data Index: 1963765 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.9437. Min Act: -0.1700
Data Index: 1782220 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.8812. Min Act: -0.1700
Data Index: 1411453 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.8812. Min Act: -0.1700
Data Index: 5092558 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.8499. Min Act: -0.1700
Data Index: 3892003 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.7249. Min Act: -0.1700
Data Index: 6193163 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.7249. Min Act: -0.1700
Data Index: 8821768 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.7249. Min Act: -0.1700
Data Index: 5176062 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.7562. Min Act: -0.1700
Data Index: 6226163 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.7249. Min Act: -0.1700
Data Index: 3401453 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.6937. Min Act: -0.1700
Data Index: 2001273 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.6937. Min Act: -0.1700
Data Index: 7954771 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.6624. Min Act: -0.1700
Data Index: 110438 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.6624. Min Act: -0.1700
Data Index: 6596674 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.6312. Min Act: -0.1700
Data Index: 5006252 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.6312. Min Act: -0.1700
Data Index: 8077723 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.5999. Min Act: -0.1700
Data Index: 3053274 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.5999. Min Act: -0.1700
Data Index: 7091283 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1937. Min Range: -6.1937
Max Act: 5.5999. Min Act: -0.1700
Data Index: 4169712 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19