Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7608. Min Range: -8.7608
Max Act: 8.7608. Min Act: -0.1700
Data Index: 3682109 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7608. Min Range: -8.7608
Max Act: 8.2920. Min Act: -0.1700
Data Index: 2433855 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7608. Min Range: -8.7608
Max Act: 8.1358. Min Act: -0.1700
Data Index: 173871 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7608. Min Range: -8.7608
Max Act: 8.1045. Min Act: -0.1700
Data Index: 3552248 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7608. Min Range: -8.7608
Max Act: 8.1358. Min Act: -0.1700
Data Index: 3682108 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.9795. Min Act: -0.1700
Data Index: 2433854 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.8858. Min Act: -0.1700
Data Index: 7149627 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.9483. Min Act: -0.1700
Data Index: 3552246 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.7920. Min Act: -0.1700
Data Index: 3552249 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.7608. Min Act: -0.1700
Data Index: 3552237 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.7608. Min Act: -0.1700
Data Index: 6110453 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.7608. Min Act: -0.1700
Data Index: 8805164 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.7295. Min Act: -0.1700
Data Index: 4401958 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.7608. Min Act: -0.1700
Data Index: 7194159 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.7295. Min Act: -0.1700
Data Index: 173870 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.6983. Min Act: -0.1700
Data Index: 932737 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.6983. Min Act: -0.1700
Data Index: 7654234 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.6983. Min Act: -0.1700
Data Index: 4401957 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.6358. Min Act: -0.1700
Data Index: 4859876 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7608. Min Range: -8.7608
Max Act: 7.6983. Min Act: -0.1700
Data Index: 3552247 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19