Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2207 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.7632. Min Act: -0.1700
Data Index: 3997877 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.6694. Min Act: -0.1700
Data Index: 2996016 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.6069. Min Act: -0.1700
Data Index: 3007725 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.6069. Min Act: -0.1700
Data Index: 3575589 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.5132. Min Act: -0.1700
Data Index: 1015817 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.5132. Min Act: -0.1700
Data Index: 8673614 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.5132. Min Act: -0.1700
Data Index: 5820791 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.5132. Min Act: -0.1700
Data Index: 8261301 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.4819. Min Act: -0.1700
Data Index: 1911914 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.4507. Min Act: -0.1700
Data Index: 5787919 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.4819. Min Act: -0.1700
Data Index: 7891804 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.4194. Min Act: -0.1700
Data Index: 5811195 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.4194. Min Act: -0.1700
Data Index: 8140294 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.3882. Min Act: -0.1700
Data Index: 7256953 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.3882. Min Act: -0.1700
Data Index: 6492594 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.3882. Min Act: -0.1700
Data Index: 5681917 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.3882. Min Act: -0.1700
Data Index: 3289913 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.3257. Min Act: -0.1700
Data Index: 6492595 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.3569. Min Act: -0.1700
Data Index: 1828338 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7632. Min Range: -6.7632
Max Act: 6.2944. Min Act: -0.1700
Data Index: 5219645 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19