Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5125 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.8922. Min Act: -0.1700
Data Index: 3274889 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.6422. Min Act: -0.1700
Data Index: 7192821 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.6109. Min Act: -0.1700
Data Index: 6212233 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.6109. Min Act: -0.1700
Data Index: 5777979 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.5797. Min Act: -0.1700
Data Index: 3082686 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.5172. Min Act: -0.1700
Data Index: 5857525 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.5172. Min Act: -0.1700
Data Index: 4065706 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.4859. Min Act: -0.1700
Data Index: 2274193 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.4547. Min Act: -0.1700
Data Index: 8294750 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.4547. Min Act: -0.1700
Data Index: 3055230 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2672. Min Act: -0.1700
Data Index: 1992473 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2359. Min Act: -0.1700
Data Index: 5887370 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.2047. Min Act: -0.1700
Data Index: 3335164 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.1734. Min Act: -0.1700
Data Index: 3338913 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.1734. Min Act: -0.1700
Data Index: 4085614 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.1422. Min Act: -0.1700
Data Index: 408627 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.1734. Min Act: -0.1700
Data Index: 32628 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.1734. Min Act: -0.1700
Data Index: 1553448 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.1734. Min Act: -0.1700
Data Index: 7960387 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8922. Min Range: -6.8922
Max Act: 6.1734. Min Act: -0.1700
Data Index: 6645090 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19