Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1397 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.8988. Min Act: -0.1700
Data Index: 6686272 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7425. Min Act: -0.1700
Data Index: 7006003 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7425. Min Act: -0.1700
Data Index: 313892 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7113. Min Act: -0.1700
Data Index: 4976218 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7113. Min Act: -0.1700
Data Index: 7516454 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 2850907 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7113. Min Act: -0.1700
Data Index: 7503361 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 1903096 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 7055525 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.7113. Min Act: -0.1700
Data Index: 2448291 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 7466901 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 2574467 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 3246534 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 6180297 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 814641 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 6387315 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 3994940 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 6548374 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 4879244 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8988. Min Range: -6.8988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 8262739 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19