Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2294. Min Range: -7.2294
Max Act: 7.2294. Min Act: -0.1700
Data Index: 8814781 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2294. Min Range: -7.2294
Max Act: 7.1982. Min Act: -0.1700
Data Index: 5205728 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2294. Min Range: -7.2294
Max Act: 7.0107. Min Act: -0.1700
Data Index: 1463225 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.7607. Min Act: -0.1700
Data Index: 3832454 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.6669. Min Act: -0.1700
Data Index: 6711597 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.6044. Min Act: -0.1700
Data Index: 3706297 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.5732. Min Act: -0.1700
Data Index: 7450907 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.5419. Min Act: -0.1700
Data Index: 1133093 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.5419. Min Act: -0.1700
Data Index: 2835047 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.4794. Min Act: -0.1700
Data Index: 5585766 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.5419. Min Act: -0.1700
Data Index: 2707948 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.4794. Min Act: -0.1700
Data Index: 1139589 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.4794. Min Act: -0.1700
Data Index: 3902574 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.4482. Min Act: -0.1700
Data Index: 4866233 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.4482. Min Act: -0.1700
Data Index: 5428063 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.4169. Min Act: -0.1700
Data Index: 2132145 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.4169. Min Act: -0.1700
Data Index: 6316953 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.4169. Min Act: -0.1700
Data Index: 6767567 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.4169. Min Act: -0.1700
Data Index: 14344 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2294. Min Range: -7.2294
Max Act: 6.3857. Min Act: -0.1700
Data Index: 3532727 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19