Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1874 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8958. Min Act: -0.1700
Data Index: 2955545 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8646. Min Act: -0.1700
Data Index: 487363 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8646. Min Act: -0.1700
Data Index: 6420442 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8333. Min Act: -0.1700
Data Index: 2739783 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8333. Min Act: -0.1700
Data Index: 1853412 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8021. Min Act: -0.1700
Data Index: 1075394 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.8021. Min Act: -0.1700
Data Index: 13437 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.7083. Min Act: -0.1700
Data Index: 2172174 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.7396. Min Act: -0.1700
Data Index: 7067681 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.7083. Min Act: -0.1700
Data Index: 7422192 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6771. Min Act: -0.1700
Data Index: 3109165 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6771. Min Act: -0.1700
Data Index: 8108389 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6458. Min Act: -0.1700
Data Index: 2046120 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6771. Min Act: -0.1700
Data Index: 6916154 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6771. Min Act: -0.1700
Data Index: 3707867 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6771. Min Act: -0.1700
Data Index: 7638142 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6458. Min Act: -0.1700
Data Index: 843745 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6146. Min Act: -0.1700
Data Index: 3980440 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6146. Min Act: -0.1700
Data Index: 288011 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8958. Min Range: -5.8958
Max Act: 5.6146. Min Act: -0.1700
Data Index: 332624 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19