Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6071 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1064. Min Range: -10.1064
Max Act: 10.1064. Min Act: -0.1700
Data Index: 1946395 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.9189. Min Act: -0.1700
Data Index: 5217728 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.8564. Min Act: -0.1700
Data Index: 3372419 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.6689. Min Act: -0.1700
Data Index: 6861489 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.6064. Min Act: -0.1700
Data Index: 370794 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.6064. Min Act: -0.1700
Data Index: 8415585 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.6064. Min Act: -0.1700
Data Index: 3516408 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.6064. Min Act: -0.1700
Data Index: 8223946 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.5439. Min Act: -0.1700
Data Index: 8235537 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.4814. Min Act: -0.1700
Data Index: 30413 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.4189. Min Act: -0.1700
Data Index: 2631533 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.4189. Min Act: -0.1700
Data Index: 3746439 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.4189. Min Act: -0.1700
Data Index: 373795 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.3564. Min Act: -0.1700
Data Index: 8345687 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.3564. Min Act: -0.1700
Data Index: 2777783 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.3564. Min Act: -0.1700
Data Index: 1907693 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.3564. Min Act: -0.1700
Data Index: 6990388 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.2939. Min Act: -0.1700
Data Index: 6341081 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.3564. Min Act: -0.1700
Data Index: 3104383 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1064. Min Range: -10.1064
Max Act: 9.3564. Min Act: -0.1700
Data Index: 6989533 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19