Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1623 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.3466. Min Act: -0.1700
Data Index: 1075927 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.2210. Min Act: -0.1700
Data Index: 5272634 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.2053. Min Act: -0.1700
Data Index: 8415461 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.1581. Min Act: -0.1700
Data Index: 5640996 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.1423. Min Act: -0.1700
Data Index: 6577765 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0793. Min Act: -0.1700
Data Index: 5046633 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0477. Min Act: -0.1700
Data Index: 5284255 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0635. Min Act: -0.1700
Data Index: 6347012 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0162. Min Act: -0.1700
Data Index: 8116409 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0477. Min Act: -0.1700
Data Index: 8130022 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0320. Min Act: -0.1700
Data Index: 6775233 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0320. Min Act: -0.1700
Data Index: 8468981 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0320. Min Act: -0.1700
Data Index: 8681559 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0162. Min Act: -0.1700
Data Index: 5177800 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0162. Min Act: -0.1700
Data Index: 7558487 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0162. Min Act: -0.1700
Data Index: 6323875 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0004. Min Act: -0.1700
Data Index: 5510651 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3466. Min Range: -3.3466
Max Act: 3.0477. Min Act: -0.1700
Data Index: 6248344 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3466. Min Range: -3.3466
Max Act: 2.9846. Min Act: -0.1700
Data Index: 5078429 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3466. Min Range: -3.3466
Max Act: 2.9687. Min Act: -0.1700
Data Index: 646056 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19