Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3788 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.9968. Min Act: -0.1700
Data Index: 1160877 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.9343. Min Act: -0.1700
Data Index: 668975 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.9343. Min Act: -0.1700
Data Index: 8397653 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.9343. Min Act: -0.1700
Data Index: 2185474 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.9343. Min Act: -0.1700
Data Index: 4929577 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.9030. Min Act: -0.1700
Data Index: 6812886 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.9030. Min Act: -0.1700
Data Index: 5182203 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.8405. Min Act: -0.1700
Data Index: 8773648 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.8405. Min Act: -0.1700
Data Index: 6131883 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.8405. Min Act: -0.1700
Data Index: 3769715 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.8405. Min Act: -0.1700
Data Index: 2538541 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.8405. Min Act: -0.1700
Data Index: 8345542 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.7780. Min Act: -0.1700
Data Index: 6484500 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.8093. Min Act: -0.1700
Data Index: 3708034 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.8093. Min Act: -0.1700
Data Index: 8325874 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.8093. Min Act: -0.1700
Data Index: 5826532 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.8093. Min Act: -0.1700
Data Index: 1201534 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.8093. Min Act: -0.1700
Data Index: 2637532 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.7780. Min Act: -0.1700
Data Index: 6984360 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9968. Min Range: -4.9968
Max Act: 4.7780. Min Act: -0.1700
Data Index: 7456787 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19