Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0098. Min Range: -6.0098
Max Act: 6.0098. Min Act: -0.1700
Data Index: 7459757 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.9473. Min Act: -0.1700
Data Index: 1093477 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.8848. Min Act: -0.1700
Data Index: 4852522 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.8536. Min Act: -0.1700
Data Index: 1412648 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.8536. Min Act: -0.1700
Data Index: 8775829 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.7911. Min Act: -0.1700
Data Index: 732651 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.7598. Min Act: -0.1700
Data Index: 2746064 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.7598. Min Act: -0.1700
Data Index: 5228108 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.7286. Min Act: -0.1700
Data Index: 4668972 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.7598. Min Act: -0.1700
Data Index: 3041182 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.7286. Min Act: -0.1700
Data Index: 8698812 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.6973. Min Act: -0.1700
Data Index: 5355256 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.6973. Min Act: -0.1700
Data Index: 2596838 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.6661. Min Act: -0.1700
Data Index: 359061 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.6661. Min Act: -0.1700
Data Index: 5422409 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.6661. Min Act: -0.1700
Data Index: 8662766 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.6661. Min Act: -0.1700
Data Index: 6839017 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.6348. Min Act: -0.1700
Data Index: 1517228 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.6036. Min Act: -0.1700
Data Index: 5147578 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0098. Min Range: -6.0098
Max Act: 5.6036. Min Act: -0.1700
Data Index: 3791340 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19