Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5514 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.3541. Min Act: -0.1700
Data Index: 6644530 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.3384. Min Act: -0.1700
Data Index: 3540814 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.3384. Min Act: -0.1700
Data Index: 7798989 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.3228. Min Act: -0.1700
Data Index: 2682194 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.3071. Min Act: -0.1700
Data Index: 2542689 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.2914. Min Act: -0.1700
Data Index: 7011706 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.2914. Min Act: -0.1700
Data Index: 5378210 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.2757. Min Act: -0.1700
Data Index: 6575381 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.2600. Min Act: -0.1700
Data Index: 4996766 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.1971. Min Act: -0.1700
Data Index: 8485978 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.2128. Min Act: -0.1700
Data Index: 3990430 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.2128. Min Act: -0.1700
Data Index: 654938 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.1971. Min Act: -0.1700
Data Index: 122215 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.2128. Min Act: -0.1700
Data Index: 3473699 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.1971. Min Act: -0.1700
Data Index: 1155782 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.1499. Min Act: -0.1700
Data Index: 344083 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.1656. Min Act: -0.1700
Data Index: 6053518 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.1656. Min Act: -0.1700
Data Index: 5978709 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.1499. Min Act: -0.1700
Data Index: 654942 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3541. Min Range: -3.3541
Max Act: 3.1341. Min Act: -0.1700
Data Index: 6272577 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19