Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1421 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.8232. Min Act: -0.1700
Data Index: 6786687 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.8232. Min Act: -0.1700
Data Index: 175877 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.7607. Min Act: -0.1700
Data Index: 6944391 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.7607. Min Act: -0.1700
Data Index: 5547079 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.6982. Min Act: -0.1700
Data Index: 7245810 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.6982. Min Act: -0.1700
Data Index: 2707378 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.6982. Min Act: -0.1700
Data Index: 2637290 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.6357. Min Act: -0.1700
Data Index: 5753767 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.6357. Min Act: -0.1700
Data Index: 778565 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.5732. Min Act: -0.1700
Data Index: 480659 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.5732. Min Act: -0.1700
Data Index: 8787423 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.5732. Min Act: -0.1700
Data Index: 5073467 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.5107. Min Act: -0.1700
Data Index: 2387663 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.5107. Min Act: -0.1700
Data Index: 2734306 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.4795. Min Act: -0.1700
Data Index: 6693153 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.4170. Min Act: -0.1700
Data Index: 4459410 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.3545. Min Act: -0.1700
Data Index: 4932445 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.3857. Min Act: -0.1700
Data Index: 5115214 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.4170. Min Act: -0.1700
Data Index: 7739602 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8232. Min Range: -7.8232
Max Act: 7.3545. Min Act: -0.1700
Data Index: 5195065 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19