Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2159. Min Range: -3.2159
Max Act: 3.2159. Min Act: -0.1700
Data Index: 1785344 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2159. Min Range: -3.2159
Max Act: 3.1215. Min Act: -0.1696
Data Index: 2970039 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.9953. Min Act: -0.1700
Data Index: 5201876 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.9953. Min Act: -0.1698
Data Index: 5114991 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.9636. Min Act: -0.1700
Data Index: 236120 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.9320. Min Act: -0.1700
Data Index: 1154710 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.9320. Min Act: -0.1700
Data Index: 8343334 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.8844. Min Act: -0.1700
Data Index: 6213646 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.9161. Min Act: -0.1700
Data Index: 236108 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.9003. Min Act: -0.1700
Data Index: 236102 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.9003. Min Act: -0.1700
Data Index: 236117 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.8844. Min Act: -0.1699
Data Index: 4739789 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.8844. Min Act: -0.1700
Data Index: 8279101 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.8685. Min Act: -0.1697
Data Index: 5832301 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.8685. Min Act: -0.1700
Data Index: 236106 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.8685. Min Act: -0.1700
Data Index: 4438084 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.8527. Min Act: -0.1700
Data Index: 7967163 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.8685. Min Act: -0.1577
Data Index: 2015825 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.8527. Min Act: -0.1700
Data Index: 236109 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2159. Min Range: -3.2159
Max Act: 2.8527. Min Act: -0.1700
Data Index: 236116 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19