Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.9344. Min Act: -0.1700
Data Index: 5005243 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.6844. Min Act: -0.1700
Data Index: 5005244 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.6532. Min Act: -0.1700
Data Index: 5728707 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.5907. Min Act: -0.1700
Data Index: 7079127 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.3094. Min Act: -0.1700
Data Index: 7191974 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.3094. Min Act: -0.1700
Data Index: 5477745 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.2157. Min Act: -0.1700
Data Index: 2096300 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.2157. Min Act: -0.1700
Data Index: 4279821 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.1844. Min Act: -0.1700
Data Index: 7718986 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.1844. Min Act: -0.1700
Data Index: 7860009 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.1532. Min Act: -0.1700
Data Index: 7806753 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.1219. Min Act: -0.1700
Data Index: 7644688 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.1532. Min Act: -0.1700
Data Index: 7133369 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.0907. Min Act: -0.1700
Data Index: 1648968 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.0907. Min Act: -0.1700
Data Index: 663698 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.0594. Min Act: -0.1700
Data Index: 5968121 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.0594. Min Act: -0.1700
Data Index: 7195729 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.0594. Min Act: -0.1700
Data Index: 4596173 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9344. Min Range: -6.9344
Max Act: 5.9969. Min Act: -0.1700
Data Index: 3634871 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9344. Min Range: -6.9344
Max Act: 6.0282. Min Act: -0.1700
Data Index: 4621967 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19