Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1128 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0525. Min Range: -4.0525
Max Act: 4.0525. Min Act: -0.1700
Data Index: 7123624 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9900. Min Act: -0.1700
Data Index: 5054744 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9588. Min Act: -0.1700
Data Index: 3251450 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8962. Min Act: -0.1700
Data Index: 4398986 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8962. Min Act: -0.1700
Data Index: 7416600 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8962. Min Act: -0.1700
Data Index: 4613643 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8962. Min Act: -0.1700
Data Index: 474659 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8962. Min Act: -0.1700
Data Index: 8491111 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8650. Min Act: -0.1700
Data Index: 8570512 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8650. Min Act: -0.1700
Data Index: 7919067 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8650. Min Act: -0.1700
Data Index: 7684977 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8650. Min Act: -0.1700
Data Index: 8711435 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8337. Min Act: -0.1700
Data Index: 2939886 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8337. Min Act: -0.1700
Data Index: 3279871 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8337. Min Act: -0.1700
Data Index: 5081228 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8337. Min Act: -0.1700
Data Index: 8524003 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8024. Min Act: -0.1700
Data Index: 6518201 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8024. Min Act: -0.1700
Data Index: 4323179 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8024. Min Act: -0.1700
Data Index: 5522700 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.8024. Min Act: -0.1700
Data Index: 5527356 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19