Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 841 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.9742. Min Act: -0.1700
Data Index: 2614979 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.9429. Min Act: -0.1700
Data Index: 6874428 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.8804. Min Act: -0.1700
Data Index: 2934552 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.8179. Min Act: -0.1700
Data Index: 2089596 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.8179. Min Act: -0.1700
Data Index: 8022962 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.7867. Min Act: -0.1700
Data Index: 5238213 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.7554. Min Act: -0.1700
Data Index: 6886470 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.7554. Min Act: -0.1700
Data Index: 4862330 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.7242. Min Act: -0.1700
Data Index: 5583213 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.7242. Min Act: -0.1700
Data Index: 1634934 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.7554. Min Act: -0.1700
Data Index: 3272369 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.6929. Min Act: -0.1700
Data Index: 1780244 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.6929. Min Act: -0.1700
Data Index: 2377652 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.6929. Min Act: -0.1700
Data Index: 3846049 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.7242. Min Act: -0.1700
Data Index: 4506181 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.6929. Min Act: -0.1700
Data Index: 7321201 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.6617. Min Act: -0.1700
Data Index: 2469112 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.6929. Min Act: -0.1700
Data Index: 7142202 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.6304. Min Act: -0.1700
Data Index: 4628923 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9742. Min Range: -4.9742
Max Act: 4.6304. Min Act: -0.1700
Data Index: 2749800 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19