Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.7071. Min Act: -0.1700
Data Index: 6541050 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.5821. Min Act: -0.1700
Data Index: 392384 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.5821. Min Act: -0.1700
Data Index: 92771 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.5821. Min Act: -0.1700
Data Index: 8465058 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.5821. Min Act: -0.1700
Data Index: 371563 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.5821. Min Act: -0.1700
Data Index: 8268383 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.6134. Min Act: -0.1700
Data Index: 6133862 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.4884. Min Act: -0.1700
Data Index: 7556705 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.4884. Min Act: -0.1700
Data Index: 161782 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.4571. Min Act: -0.1700
Data Index: 6329871 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.4571. Min Act: -0.1700
Data Index: 3752329 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.4884. Min Act: -0.1700
Data Index: 5974189 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.4571. Min Act: -0.1700
Data Index: 5093870 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.4571. Min Act: -0.1700
Data Index: 7016692 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.3946. Min Act: -0.1700
Data Index: 6545439 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.3946. Min Act: -0.1700
Data Index: 1524038 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.3634. Min Act: -0.1700
Data Index: 578423 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.3634. Min Act: -0.1700
Data Index: 2822162 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.3946. Min Act: -0.1700
Data Index: 6268657 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7071. Min Range: -6.7071
Max Act: 6.3321. Min Act: -0.1700
Data Index: 857224 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19