Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1964 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.8564. Min Act: -0.1700
Data Index: 3137302 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.8252. Min Act: -0.1700
Data Index: 5319461 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.8252. Min Act: -0.1700
Data Index: 6851534 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.7939. Min Act: -0.1700
Data Index: 4146158 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.7939. Min Act: -0.1700
Data Index: 2189819 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.7314. Min Act: -0.1700
Data Index: 1664815 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.7002. Min Act: -0.1700
Data Index: 6316492 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.7002. Min Act: -0.1700
Data Index: 202692 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.7002. Min Act: -0.1700
Data Index: 2958279 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.6689. Min Act: -0.1700
Data Index: 4828360 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.6689. Min Act: -0.1700
Data Index: 404430 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.6064. Min Act: -0.1700
Data Index: 1993221 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.6064. Min Act: -0.1700
Data Index: 755812 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.5752. Min Act: -0.1700
Data Index: 577369 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.5752. Min Act: -0.1700
Data Index: 5313977 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.4814. Min Act: -0.1700
Data Index: 4399953 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.4814. Min Act: -0.1700
Data Index: 6923415 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.4814. Min Act: -0.1700
Data Index: 233199 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.4502. Min Act: -0.1700
Data Index: 4436599 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8564. Min Range: -6.8564
Max Act: 6.4814. Min Act: -0.1700
Data Index: 1618861 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19