Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6988. Min Act: -0.1700
Data Index: 859109 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6507. Min Act: -0.1700
Data Index: 4734264 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6347. Min Act: -0.1700
Data Index: 5580459 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6347. Min Act: -0.1700
Data Index: 7273184 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6186. Min Act: -0.1700
Data Index: 3332788 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6186. Min Act: -0.1700
Data Index: 4978301 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6186. Min Act: -0.1700
Data Index: 5604874 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6186. Min Act: -0.1700
Data Index: 1937625 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6186. Min Act: -0.1700
Data Index: 5847222 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6186. Min Act: -0.1700
Data Index: 7943937 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6025. Min Act: -0.1700
Data Index: 6485223 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6186. Min Act: -0.1700
Data Index: 7943381 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.5864. Min Act: -0.1700
Data Index: 8265976 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6025. Min Act: -0.1700
Data Index: 2011698 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.5864. Min Act: -0.1700
Data Index: 807703 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6025. Min Act: -0.1700
Data Index: 278090 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6025. Min Act: -0.1700
Data Index: 1587833 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6025. Min Act: -0.1700
Data Index: 2872679 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6025. Min Act: -0.1700
Data Index: 1212966 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6988. Min Range: -2.6988
Max Act: 2.6025. Min Act: -0.1700
Data Index: 522866 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19