Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3179 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.6770. Min Act: -0.1700
Data Index: 3308533 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.5833. Min Act: -0.1700
Data Index: 3767628 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.5520. Min Act: -0.1700
Data Index: 7704468 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.4895. Min Act: -0.1700
Data Index: 266471 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.4583. Min Act: -0.1700
Data Index: 5555429 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.4583. Min Act: -0.1700
Data Index: 2505188 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.4583. Min Act: -0.1700
Data Index: 4430592 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.4270. Min Act: -0.1700
Data Index: 3148632 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.4270. Min Act: -0.1700
Data Index: 1827612 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3958. Min Act: -0.1700
Data Index: 7549097 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3958. Min Act: -0.1700
Data Index: 728007 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3958. Min Act: -0.1700
Data Index: 2451144 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3645. Min Act: -0.1700
Data Index: 1402927 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3645. Min Act: -0.1700
Data Index: 3697621 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3645. Min Act: -0.1700
Data Index: 3996523 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3645. Min Act: -0.1700
Data Index: 815369 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3333. Min Act: -0.1700
Data Index: 8528351 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3333. Min Act: -0.1700
Data Index: 3996522 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3333. Min Act: -0.1700
Data Index: 7882945 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6770. Min Range: -5.6770
Max Act: 5.3333. Min Act: -0.1700
Data Index: 1048192 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19