Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.3614. Min Act: -0.1700
Data Index: 1872581 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.3614. Min Act: -0.1700
Data Index: 4403802 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.2364. Min Act: -0.1700
Data Index: 3062614 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1739. Min Act: -0.1700
Data Index: 2038344 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1739. Min Act: -0.1700
Data Index: 3294376 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1739. Min Act: -0.1700
Data Index: 7629518 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.1114. Min Act: -0.1700
Data Index: 7751336 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0801. Min Act: -0.1700
Data Index: 2478547 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0801. Min Act: -0.1700
Data Index: 777472 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0801. Min Act: -0.1700
Data Index: 3847430 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0489. Min Act: -0.1700
Data Index: 5400076 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0489. Min Act: -0.1700
Data Index: 4479342 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0489. Min Act: -0.1700
Data Index: 277342 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0489. Min Act: -0.1700
Data Index: 6789498 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0489. Min Act: -0.1700
Data Index: 1102934 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0489. Min Act: -0.1700
Data Index: 6453418 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0176. Min Act: -0.1700
Data Index: 7542357 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0176. Min Act: -0.1700
Data Index: 2484977 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3614. Min Range: -4.3614
Max Act: 4.0176. Min Act: -0.1700
Data Index: 6132409 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3614. Min Range: -4.3614
Max Act: 3.9551. Min Act: -0.1700
Data Index: 6293282 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19