Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.8090. Min Act: -0.1700
Data Index: 7271996 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.4965. Min Act: -0.1700
Data Index: 3457084 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.3402. Min Act: -0.1700
Data Index: 7371933 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.3715. Min Act: -0.1700
Data Index: 2670095 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.3402. Min Act: -0.1700
Data Index: 8045072 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.3402. Min Act: -0.1700
Data Index: 4247532 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.2777. Min Act: -0.1700
Data Index: 6226352 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.2465. Min Act: -0.1700
Data Index: 18041 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.2777. Min Act: -0.1700
Data Index: 5694073 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.2465. Min Act: -0.1700
Data Index: 5788814 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.2152. Min Act: -0.1700
Data Index: 7105044 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.2152. Min Act: -0.1700
Data Index: 158332 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.2465. Min Act: -0.1700
Data Index: 415888 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.1840. Min Act: -0.1700
Data Index: 1358556 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.1840. Min Act: -0.1700
Data Index: 3290818 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.1527. Min Act: -0.1700
Data Index: 6105181 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.1527. Min Act: -0.1700
Data Index: 2257780 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.1527. Min Act: -0.1700
Data Index: 3351785 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.1527. Min Act: -0.1700
Data Index: 6379522 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8090. Min Range: -5.8090
Max Act: 5.1527. Min Act: -0.1700
Data Index: 4574138 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19