Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.8711. Min Act: -0.1700
Data Index: 5814253 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.7460. Min Act: -0.1700
Data Index: 5975118 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.7147. Min Act: -0.1700
Data Index: 8134171 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.6834. Min Act: -0.1700
Data Index: 2383511 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.6990. Min Act: -0.1700
Data Index: 6177628 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.6052. Min Act: -0.1700
Data Index: 5190557 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.6365. Min Act: -0.1700
Data Index: 2467805 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.6208. Min Act: -0.1700
Data Index: 8713683 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.6208. Min Act: -0.1700
Data Index: 5696878 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.6208. Min Act: -0.1700
Data Index: 7637964 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.5895. Min Act: -0.1700
Data Index: 8553941 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.6052. Min Act: -0.1700
Data Index: 5894655 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.6208. Min Act: -0.1700
Data Index: 1901948 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.5895. Min Act: -0.1700
Data Index: 8279360 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.6052. Min Act: -0.1700
Data Index: 8144031 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.5582. Min Act: -0.1700
Data Index: 5829132 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.5895. Min Act: -0.1700
Data Index: 3618989 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.5738. Min Act: -0.1700
Data Index: 5368571 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.5582. Min Act: -0.1700
Data Index: 6322650 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8711. Min Range: -3.8711
Max Act: 3.5738. Min Act: -0.1700
Data Index: 5214288 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19