Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.7758. Min Act: -0.1700
Data Index: 2698949 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.7446. Min Act: -0.1700
Data Index: 1887241 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.5883. Min Act: -0.1700
Data Index: 7630925 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.4633. Min Act: -0.1700
Data Index: 1307813 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.4633. Min Act: -0.1700
Data Index: 1725516 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.4633. Min Act: -0.1700
Data Index: 5677448 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.4008. Min Act: -0.1700
Data Index: 4429736 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.4008. Min Act: -0.1700
Data Index: 6963941 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.3696. Min Act: -0.1700
Data Index: 6579151 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.3696. Min Act: -0.1700
Data Index: 467462 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.3383. Min Act: -0.1700
Data Index: 6944597 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.3383. Min Act: -0.1700
Data Index: 1801913 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.3383. Min Act: -0.1700
Data Index: 4543062 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.3071. Min Act: -0.1700
Data Index: 5378077 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.3071. Min Act: -0.1700
Data Index: 7927892 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.2758. Min Act: -0.1700
Data Index: 6457421 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.2758. Min Act: -0.1700
Data Index: 5913006 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.2758. Min Act: -0.1700
Data Index: 4833728 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.2446. Min Act: -0.1700
Data Index: 2848207 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7758. Min Range: -6.7758
Max Act: 6.2133. Min Act: -0.1700
Data Index: 5510953 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19