Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.5907. Min Act: -0.1700
Data Index: 2957342 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.3086. Min Act: -0.1700
Data Index: 1496661 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.2615. Min Act: -0.1700
Data Index: 2041725 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.2301. Min Act: -0.1700
Data Index: 6954674 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.2144. Min Act: -0.1700
Data Index: 428102 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1987. Min Act: -0.1700
Data Index: 679851 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.2144. Min Act: -0.1700
Data Index: 5011453 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1987. Min Act: -0.1700
Data Index: 3378631 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1829. Min Act: -0.1700
Data Index: 1387220 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1515. Min Act: -0.1700
Data Index: 8791120 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1515. Min Act: -0.1700
Data Index: 158366 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1672. Min Act: -0.1700
Data Index: 6233712 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1515. Min Act: -0.1700
Data Index: 2240131 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1357. Min Act: -0.1700
Data Index: 1665133 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1042. Min Act: -0.1700
Data Index: 7056933 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.0884. Min Act: -0.1700
Data Index: 1798319 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1042. Min Act: -0.1700
Data Index: 6396484 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1042. Min Act: -0.1700
Data Index: 991021 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.0884. Min Act: -0.1700
Data Index: 973064 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5907. Min Range: -3.5907
Max Act: 3.1042. Min Act: -0.1700
Data Index: 3256986 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19