Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 80 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.9157. Min Act: -0.1700
Data Index: 6312895 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7886. Min Act: -0.1700
Data Index: 6476199 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7727. Min Act: -0.1700
Data Index: 6312881 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7727. Min Act: -0.1700
Data Index: 2938643 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7248. Min Act: -0.1700
Data Index: 5474767 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7407. Min Act: -0.1700
Data Index: 6476204 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7407. Min Act: -0.1700
Data Index: 6810384 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7407. Min Act: -0.1700
Data Index: 1424779 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7248. Min Act: -0.1700
Data Index: 5216128 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7248. Min Act: -0.1700
Data Index: 3045337 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7088. Min Act: -0.1700
Data Index: 7317144 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7088. Min Act: -0.1700
Data Index: 2938653 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7088. Min Act: -0.1700
Data Index: 3798442 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7088. Min Act: -0.1700
Data Index: 6032410 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7088. Min Act: -0.1700
Data Index: 6132141 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7088. Min Act: -0.1700
Data Index: 2195717 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7088. Min Act: -0.1700
Data Index: 7040478 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.7088. Min Act: -0.1700
Data Index: 6811840 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.6928. Min Act: -0.1700
Data Index: 5362844 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9157. Min Range: -2.9157
Max Act: 2.6928. Min Act: -0.1700
Data Index: 6312877 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19