Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.8201. Min Act: -0.1700
Data Index: 1072416 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.7888. Min Act: -0.1700
Data Index: 5545268 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.7888. Min Act: -0.1700
Data Index: 6863264 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.7576. Min Act: -0.1700
Data Index: 6065759 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.7576. Min Act: -0.1700
Data Index: 7739972 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.7263. Min Act: -0.1700
Data Index: 7129792 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.7263. Min Act: -0.1700
Data Index: 3323265 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6951. Min Act: -0.1700
Data Index: 2526994 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6638. Min Act: -0.1700
Data Index: 7029548 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6638. Min Act: -0.1700
Data Index: 8075062 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6638. Min Act: -0.1700
Data Index: 3177505 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6638. Min Act: -0.1700
Data Index: 4420482 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6638. Min Act: -0.1700
Data Index: 4082685 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6638. Min Act: -0.1700
Data Index: 5619845 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6326. Min Act: -0.1700
Data Index: 5870144 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6638. Min Act: -0.1700
Data Index: 1194257 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6326. Min Act: -0.1700
Data Index: 7875554 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6326. Min Act: -0.1700
Data Index: 5715013 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6326. Min Act: -0.1700
Data Index: 4532982 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8201. Min Range: -6.8201
Max Act: 6.6013. Min Act: -0.1700
Data Index: 946130 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19