Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.9113. Min Act: -0.1700
Data Index: 8609005 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.8488. Min Act: -0.1700
Data Index: 8276914 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.7863. Min Act: -0.1700
Data Index: 5311567 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.7238. Min Act: -0.1700
Data Index: 4684502 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.6925. Min Act: -0.1700
Data Index: 340360 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.6613. Min Act: -0.1700
Data Index: 31826 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5988. Min Act: -0.1700
Data Index: 2426620 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5988. Min Act: -0.1700
Data Index: 5933301 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5675. Min Act: -0.1700
Data Index: 7410555 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5675. Min Act: -0.1700
Data Index: 3413673 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5988. Min Act: -0.1700
Data Index: 2376524 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5363. Min Act: -0.1700
Data Index: 4102646 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5363. Min Act: -0.1700
Data Index: 6062686 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5363. Min Act: -0.1700
Data Index: 6331328 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5363. Min Act: -0.1700
Data Index: 208141 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5363. Min Act: -0.1700
Data Index: 3227870 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5363. Min Act: -0.1700
Data Index: 3789838 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5050. Min Act: -0.1700
Data Index: 3658581 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.4738. Min Act: -0.1700
Data Index: 5311584 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.4738. Min Act: -0.1700
Data Index: 1901609 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19