Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5774. Min Range: -3.5774
Max Act: 3.5774. Min Act: -0.1700
Data Index: 1948871 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5774. Min Range: -3.5774
Max Act: 3.2953. Min Act: -0.1700
Data Index: 350228 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5774. Min Range: -3.5774
Max Act: 3.1696. Min Act: -0.1700
Data Index: 4132538 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5774. Min Range: -3.5774
Max Act: 3.1381. Min Act: -0.1700
Data Index: 8515475 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5774. Min Range: -3.5774
Max Act: 3.1066. Min Act: -0.1700
Data Index: 109700 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5774. Min Range: -3.5774
Max Act: 3.1066. Min Act: -0.1700
Data Index: 7189822 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5774. Min Range: -3.5774
Max Act: 3.0435. Min Act: -0.1700
Data Index: 5840512 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5774. Min Range: -3.5774
Max Act: 3.0435. Min Act: -0.1700
Data Index: 5526393 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5774. Min Range: -3.5774
Max Act: 3.0435. Min Act: -0.1700
Data Index: 3426002 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5774. Min Range: -3.5774
Max Act: 3.0119. Min Act: -0.1700
Data Index: 3925198 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5774. Min Range: -3.5774
Max Act: 2.9803. Min Act: -0.1700
Data Index: 7935464 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5774. Min Range: -3.5774
Max Act: 2.9803. Min Act: -0.1700
Data Index: 7858869 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5774. Min Range: -3.5774
Max Act: 2.9803. Min Act: -0.1700
Data Index: 2803221 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5774. Min Range: -3.5774
Max Act: 2.9803. Min Act: -0.1700
Data Index: 5209792 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5774. Min Range: -3.5774
Max Act: 2.9803. Min Act: -0.1700
Data Index: 1687164 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5774. Min Range: -3.5774
Max Act: 2.9803. Min Act: -0.1700
Data Index: 2503488 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5774. Min Range: -3.5774
Max Act: 2.9487. Min Act: -0.1700
Data Index: 7804737 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5774. Min Range: -3.5774
Max Act: 2.9487. Min Act: -0.1700
Data Index: 1609166 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5774. Min Range: -3.5774
Max Act: 2.9328. Min Act: -0.1700
Data Index: 2124100 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5774. Min Range: -3.5774
Max Act: 2.9328. Min Act: -0.1700
Data Index: 5367935 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19