Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4322 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.5405. Min Act: -0.1700
Data Index: 3884126 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4936. Min Act: -0.1700
Data Index: 8194387 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4779. Min Act: -0.1700
Data Index: 7635027 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4779. Min Act: -0.1700
Data Index: 2671440 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4779. Min Act: -0.1700
Data Index: 1854786 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4466. Min Act: -0.1700
Data Index: 6318912 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4622. Min Act: -0.1700
Data Index: 3033765 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4466. Min Act: -0.1700
Data Index: 7543349 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4466. Min Act: -0.1700
Data Index: 5637928 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4466. Min Act: -0.1700
Data Index: 7232590 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4309. Min Act: -0.1700
Data Index: 1255548 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4152. Min Act: -0.1700
Data Index: 2797926 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4309. Min Act: -0.1700
Data Index: 4394015 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4309. Min Act: -0.1700
Data Index: 5898173 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4309. Min Act: -0.1700
Data Index: 6620922 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.4152. Min Act: -0.1700
Data Index: 6418842 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.3839. Min Act: -0.1700
Data Index: 384858 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.3995. Min Act: -0.1700
Data Index: 2875227 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.3995. Min Act: -0.1700
Data Index: 2808862 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5405. Min Range: -3.5405
Max Act: 3.3995. Min Act: -0.1700
Data Index: 2824462 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19