Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4360 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.7849. Min Act: -0.1700
Data Index: 496343 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.6599. Min Act: -0.1700
Data Index: 4106809 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.6599. Min Act: -0.1700
Data Index: 56044 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.6286. Min Act: -0.1700
Data Index: 6070018 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.6286. Min Act: -0.1700
Data Index: 6070002 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.5661. Min Act: -0.1700
Data Index: 7791799 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.5036. Min Act: -0.1700
Data Index: 3319939 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.5036. Min Act: -0.1700
Data Index: 2252030 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.4724. Min Act: -0.1700
Data Index: 3564751 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.4411. Min Act: -0.1700
Data Index: 3662965 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.4099. Min Act: -0.1700
Data Index: 8229167 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.4099. Min Act: -0.1700
Data Index: 8357983 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.4099. Min Act: -0.1700
Data Index: 8366154 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.4099. Min Act: -0.1700
Data Index: 4222577 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.4099. Min Act: -0.1700
Data Index: 6070021 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.4099. Min Act: -0.1700
Data Index: 4594121 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.3786. Min Act: -0.1700
Data Index: 4352595 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.3786. Min Act: -0.1700
Data Index: 8391797 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.3786. Min Act: -0.1700
Data Index: 2010982 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7849. Min Range: -5.7849
Max Act: 5.3474. Min Act: -0.1700
Data Index: 2599908 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19