Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0657. Min Range: -6.0657
Max Act: 6.0657. Min Act: -0.1700
Data Index: 5727340 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0657. Min Range: -6.0657
Max Act: 6.0032. Min Act: -0.1700
Data Index: 7681188 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0657. Min Range: -6.0657
Max Act: 6.0032. Min Act: -0.1700
Data Index: 1136578 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9720. Min Act: -0.1700
Data Index: 6852377 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9720. Min Act: -0.1700
Data Index: 6256447 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9407. Min Act: -0.1700
Data Index: 5264771 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9407. Min Act: -0.1700
Data Index: 8264245 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9720. Min Act: -0.1700
Data Index: 7934063 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9407. Min Act: -0.1700
Data Index: 834454 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9407. Min Act: -0.1700
Data Index: 3918465 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9407. Min Act: -0.1700
Data Index: 4923662 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9095. Min Act: -0.1700
Data Index: 2845236 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9095. Min Act: -0.1700
Data Index: 919766 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9095. Min Act: -0.1700
Data Index: 8262968 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.9095. Min Act: -0.1700
Data Index: 4918519 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.8782. Min Act: -0.1700
Data Index: 3974093 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.8782. Min Act: -0.1700
Data Index: 1705221 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.8782. Min Act: -0.1700
Data Index: 6871793 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.8782. Min Act: -0.1700
Data Index: 8790945 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0657. Min Range: -6.0657
Max Act: 5.8782. Min Act: -0.1700
Data Index: 3497196 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19