Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4417 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.9643. Min Act: -0.1700
Data Index: 5610619 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8850. Min Act: -0.1700
Data Index: 717101 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8533. Min Act: -0.1700
Data Index: 4371399 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8374. Min Act: -0.1700
Data Index: 6756935 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8374. Min Act: -0.1700
Data Index: 5797257 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8533. Min Act: -0.1700
Data Index: 1514639 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8374. Min Act: -0.1700
Data Index: 5602514 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8374. Min Act: -0.1700
Data Index: 4162325 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8215. Min Act: -0.1700
Data Index: 2758286 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8215. Min Act: -0.1700
Data Index: 2157025 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8056. Min Act: -0.1700
Data Index: 4336686 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8215. Min Act: -0.1700
Data Index: 7862605 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8056. Min Act: -0.1700
Data Index: 6666390 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.7896. Min Act: -0.1700
Data Index: 8464695 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8056. Min Act: -0.1700
Data Index: 4399898 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8056. Min Act: -0.1700
Data Index: 6657170 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.7896. Min Act: -0.1700
Data Index: 1337508 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8056. Min Act: -0.1700
Data Index: 8322342 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8056. Min Act: -0.1700
Data Index: 6421527 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9643. Min Range: -2.9643
Max Act: 2.8056. Min Act: -0.1700
Data Index: 3182139 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19