Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1948 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.9704. Min Act: -0.1699
Data Index: 6410524 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8453. Min Act: -0.1700
Data Index: 359489 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.8140. Min Act: -0.1700
Data Index: 359488 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.7515. Min Act: -0.1700
Data Index: 8815300 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.6889. Min Act: -0.1700
Data Index: 4991617 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.6889. Min Act: -0.1558
Data Index: 1244484 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.5950. Min Act: -0.1699
Data Index: 387446 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.5950. Min Act: -0.1700
Data Index: 5533586 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.5637. Min Act: -0.1627
Data Index: 382662 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.5637. Min Act: -0.1700
Data Index: 8717190 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.5324. Min Act: -0.1698
Data Index: 8528884 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.5011. Min Act: -0.1698
Data Index: 5312794 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.5011. Min Act: -0.1697
Data Index: 2767552 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.5324. Min Act: -0.1699
Data Index: 3751084 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.4698. Min Act: -0.1700
Data Index: 4304546 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.4698. Min Act: -0.1693
Data Index: 2464960 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.4384. Min Act: -0.1676
Data Index: 8531458 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.4698. Min Act: -0.1692
Data Index: 8188473 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.4384. Min Act: -0.1700
Data Index: 359487 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9704. Min Range: -3.9704
Max Act: 3.4384. Min Act: -0.1698
Data Index: 5386067 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19