Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4318 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9949. Min Act: -0.1700
Data Index: 2868086 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9949. Min Act: -0.1700
Data Index: 379830 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0261. Min Range: -6.0261
Max Act: 6.0261. Min Act: -0.1700
Data Index: 1708411 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9324. Min Act: -0.1700
Data Index: 2157000 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9636. Min Act: -0.1700
Data Index: 6190591 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9636. Min Act: -0.1700
Data Index: 4423389 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9324. Min Act: -0.1700
Data Index: 8650666 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9324. Min Act: -0.1700
Data Index: 7660921 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9011. Min Act: -0.1700
Data Index: 8523575 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9011. Min Act: -0.1700
Data Index: 7716444 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9011. Min Act: -0.1700
Data Index: 5458644 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.9011. Min Act: -0.1700
Data Index: 3775958 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.8699. Min Act: -0.1700
Data Index: 3741431 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.8699. Min Act: -0.1700
Data Index: 6199403 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.8386. Min Act: -0.1700
Data Index: 1378624 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.8386. Min Act: -0.1700
Data Index: 15853 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.8386. Min Act: -0.1700
Data Index: 5909923 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.8386. Min Act: -0.1700
Data Index: 3190406 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.8074. Min Act: -0.1700
Data Index: 1009860 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0261. Min Range: -6.0261
Max Act: 5.8074. Min Act: -0.1700
Data Index: 5766705 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19