Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4277 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.3261. Min Act: -0.1700
Data Index: 5677303 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.2636. Min Act: -0.1700
Data Index: 1200471 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.1074. Min Act: -0.1700
Data Index: 1316627 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3261. Min Range: -6.3261
Max Act: 6.0761. Min Act: -0.1700
Data Index: 2141290 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.9824. Min Act: -0.1700
Data Index: 6408624 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.9824. Min Act: -0.1700
Data Index: 1539494 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.9511. Min Act: -0.1700
Data Index: 4552961 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.8261. Min Act: -0.1700
Data Index: 5069143 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.8261. Min Act: -0.1700
Data Index: 411513 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7949. Min Act: -0.1700
Data Index: 4346106 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7949. Min Act: -0.1700
Data Index: 1316625 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7949. Min Act: -0.1700
Data Index: 1106974 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7324. Min Act: -0.1700
Data Index: 8674641 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7636. Min Act: -0.1700
Data Index: 1316626 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7636. Min Act: -0.1700
Data Index: 1223798 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7324. Min Act: -0.1700
Data Index: 5703638 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7324. Min Act: -0.1700
Data Index: 1106999 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7011. Min Act: -0.1700
Data Index: 1597404 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7324. Min Act: -0.1700
Data Index: 4453122 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3261. Min Range: -6.3261
Max Act: 5.7324. Min Act: -0.1700
Data Index: 3290926 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19