Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.8095. Min Act: -0.1700
Data Index: 629612 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.7750. Min Act: -0.1700
Data Index: 3863510 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.7750. Min Act: -0.1700
Data Index: 1974496 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.7059. Min Act: -0.1700
Data Index: 4299162 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.7059. Min Act: -0.1700
Data Index: 6272572 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.7059. Min Act: -0.1700
Data Index: 4891375 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6972. Min Act: -0.1700
Data Index: 3741279 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6972. Min Act: -0.1700
Data Index: 5839633 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.7059. Min Act: -0.1700
Data Index: 4288565 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6885. Min Act: -0.1700
Data Index: 2307201 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6885. Min Act: -0.1700
Data Index: 1099404 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6712. Min Act: -0.1700
Data Index: 7341684 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6712. Min Act: -0.1700
Data Index: 1099405 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6712. Min Act: -0.1700
Data Index: 6793964 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6712. Min Act: -0.1700
Data Index: 3514742 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6625. Min Act: -0.1700
Data Index: 5068678 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6625. Min Act: -0.1700
Data Index: 7191348 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6538. Min Act: -0.1700
Data Index: 6906223 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6625. Min Act: -0.1700
Data Index: 3882566 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8095. Min Range: -1.8095
Max Act: 1.6712. Min Act: -0.1700
Data Index: 6202631 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19