Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3132. Min Range: -6.3132
Max Act: 6.3132. Min Act: -0.1700
Data Index: 7677062 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3132. Min Range: -6.3132
Max Act: 6.1570. Min Act: -0.1700
Data Index: 1466633 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3132. Min Range: -6.3132
Max Act: 6.1257. Min Act: -0.1700
Data Index: 782844 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3132. Min Range: -6.3132
Max Act: 6.0945. Min Act: -0.1700
Data Index: 7979966 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3132. Min Range: -6.3132
Max Act: 6.0945. Min Act: -0.1700
Data Index: 2678163 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3132. Min Range: -6.3132
Max Act: 6.0320. Min Act: -0.1700
Data Index: 1610647 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3132. Min Range: -6.3132
Max Act: 6.0320. Min Act: -0.1700
Data Index: 7117620 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3132. Min Range: -6.3132
Max Act: 6.0007. Min Act: -0.1700
Data Index: 8777731 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3132. Min Range: -6.3132
Max Act: 6.0007. Min Act: -0.1700
Data Index: 3278558 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3132. Min Range: -6.3132
Max Act: 6.0007. Min Act: -0.1700
Data Index: 6475023 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3132. Min Range: -6.3132
Max Act: 5.9695. Min Act: -0.1700
Data Index: 1889804 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3132. Min Range: -6.3132
Max Act: 5.9382. Min Act: -0.1700
Data Index: 3966053 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3132. Min Range: -6.3132
Max Act: 5.9382. Min Act: -0.1700
Data Index: 77796 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3132. Min Range: -6.3132
Max Act: 5.9070. Min Act: -0.1700
Data Index: 5318860 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3132. Min Range: -6.3132
Max Act: 5.8757. Min Act: -0.1700
Data Index: 8776162 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3132. Min Range: -6.3132
Max Act: 5.8757. Min Act: -0.1700
Data Index: 1366456 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3132. Min Range: -6.3132
Max Act: 5.8445. Min Act: -0.1700
Data Index: 655249 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3132. Min Range: -6.3132
Max Act: 5.8445. Min Act: -0.1700
Data Index: 6834488 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3132. Min Range: -6.3132
Max Act: 5.8757. Min Act: -0.1700
Data Index: 1889817 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3132. Min Range: -6.3132
Max Act: 5.8757. Min Act: -0.1700
Data Index: 1110169 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19