Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1619 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.4931. Min Act: -0.1700
Data Index: 6951568 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.4306. Min Act: -0.1700
Data Index: 2188294 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.4306. Min Act: -0.1700
Data Index: 7485889 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.3994. Min Act: -0.1700
Data Index: 4362608 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.3369. Min Act: -0.1700
Data Index: 1328297 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.3056. Min Act: -0.1700
Data Index: 7097076 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2431. Min Act: -0.1700
Data Index: 3181106 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2431. Min Act: -0.1700
Data Index: 6535576 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.2119. Min Act: -0.1700
Data Index: 3031766 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1806. Min Act: -0.1700
Data Index: 1904513 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1806. Min Act: -0.1700
Data Index: 5821944 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1806. Min Act: -0.1700
Data Index: 1552025 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1806. Min Act: -0.1700
Data Index: 5953725 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1494. Min Act: -0.1700
Data Index: 6645786 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1494. Min Act: -0.1700
Data Index: 2661876 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1494. Min Act: -0.1700
Data Index: 8749487 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1494. Min Act: -0.1700
Data Index: 7428787 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1494. Min Act: -0.1700
Data Index: 8439504 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1181. Min Act: -0.1700
Data Index: 1863275 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4931. Min Range: -6.4931
Max Act: 6.1181. Min Act: -0.1700
Data Index: 1242877 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19