Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1814. Min Range: -9.1814
Max Act: 9.1814. Min Act: -0.1700
Data Index: 8324124 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.8064. Min Act: -0.1700
Data Index: 4144725 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.7439. Min Act: -0.1700
Data Index: 8816945 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.6189. Min Act: -0.1700
Data Index: 7285431 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.6189. Min Act: -0.1700
Data Index: 2054741 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.6189. Min Act: -0.1700
Data Index: 4234501 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.6189. Min Act: -0.1700
Data Index: 686280 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.4939. Min Act: -0.1700
Data Index: 7878369 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.5564. Min Act: -0.1700
Data Index: 5881934 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.5564. Min Act: -0.1700
Data Index: 5383323 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.4939. Min Act: -0.1700
Data Index: 7613368 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.4939. Min Act: -0.1700
Data Index: 1815864 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.4314. Min Act: -0.1700
Data Index: 4780495 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.3689. Min Act: -0.1700
Data Index: 1647666 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.4314. Min Act: -0.1700
Data Index: 3509968 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.4314. Min Act: -0.1700
Data Index: 417180 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.4314. Min Act: -0.1700
Data Index: 4335603 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.4314. Min Act: -0.1700
Data Index: 1216351 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.4314. Min Act: -0.1700
Data Index: 1205870 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1814. Min Range: -9.1814
Max Act: 8.4314. Min Act: -0.1700
Data Index: 5983935 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19