Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3702 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1901. Min Range: -5.1901
Max Act: 5.1901. Min Act: -0.1700
Data Index: 7979384 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1901. Min Range: -5.1901
Max Act: 5.1588. Min Act: -0.1700
Data Index: 3702900 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1901. Min Range: -5.1901
Max Act: 5.0963. Min Act: -0.1700
Data Index: 1551742 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.9713. Min Act: -0.1700
Data Index: 556471 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.9401. Min Act: -0.1700
Data Index: 1849009 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.9088. Min Act: -0.1700
Data Index: 6145897 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.9401. Min Act: -0.1700
Data Index: 3898680 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8776. Min Act: -0.1700
Data Index: 5680367 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8463. Min Act: -0.1700
Data Index: 495757 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8776. Min Act: -0.1700
Data Index: 6242646 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8776. Min Act: -0.1700
Data Index: 2305312 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8776. Min Act: -0.1700
Data Index: 7252150 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8776. Min Act: -0.1700
Data Index: 6824297 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8151. Min Act: -0.1700
Data Index: 4567641 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8463. Min Act: -0.1700
Data Index: 946314 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8463. Min Act: -0.1700
Data Index: 3926786 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8463. Min Act: -0.1700
Data Index: 2319504 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8151. Min Act: -0.1700
Data Index: 1600070 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8151. Min Act: -0.1700
Data Index: 2647168 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1901. Min Range: -5.1901
Max Act: 4.8151. Min Act: -0.1700
Data Index: 620753 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19