Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0833. Min Range: -4.0833
Max Act: 4.0833. Min Act: -0.1700
Data Index: 4567050 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0833. Min Range: -4.0833
Max Act: 4.0833. Min Act: -0.1700
Data Index: 1477362 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.9582. Min Act: -0.1700
Data Index: 5702087 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.9270. Min Act: -0.1700
Data Index: 1751299 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.9270. Min Act: -0.1700
Data Index: 160865 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.8957. Min Act: -0.1700
Data Index: 2832028 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.8644. Min Act: -0.1700
Data Index: 7036210 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.8801. Min Act: -0.1700
Data Index: 8232231 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.8488. Min Act: -0.1700
Data Index: 4128548 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.8488. Min Act: -0.1700
Data Index: 3947766 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.8488. Min Act: -0.1700
Data Index: 2517065 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.8175. Min Act: -0.1700
Data Index: 5812406 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.8175. Min Act: -0.1700
Data Index: 4025260 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.7863. Min Act: -0.1700
Data Index: 1129878 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.7706. Min Act: -0.1700
Data Index: 8243297 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.7863. Min Act: -0.1700
Data Index: 8101665 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.8019. Min Act: -0.1700
Data Index: 5151860 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.7863. Min Act: -0.1700
Data Index: 5972731 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.7706. Min Act: -0.1700
Data Index: 167351 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0833. Min Range: -4.0833
Max Act: 3.7550. Min Act: -0.1700
Data Index: 948607 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19