Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 188 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.1316. Min Act: -0.1700
Data Index: 4572743 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.1316. Min Act: -0.1700
Data Index: 4736736 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.1316. Min Act: -0.1699
Data Index: 1026099 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.1316. Min Act: -0.1700
Data Index: 3963875 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0982. Min Act: -0.1698
Data Index: 5057213 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0982. Min Act: -0.1700
Data Index: 5919595 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0814. Min Act: -0.1700
Data Index: 7521886 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0982. Min Act: -0.1700
Data Index: 6300393 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0646. Min Act: -0.1700
Data Index: 5120570 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0646. Min Act: -0.1700
Data Index: 42702 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0646. Min Act: -0.1700
Data Index: 6843005 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0646. Min Act: -0.1700
Data Index: 4270383 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0310. Min Act: -0.1700
Data Index: 192477 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0310. Min Act: -0.1700
Data Index: 8465471 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0310. Min Act: -0.1700
Data Index: 8406306 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0141. Min Act: -0.1700
Data Index: 6226198 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0310. Min Act: -0.1700
Data Index: 7629521 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0310. Min Act: -0.1700
Data Index: 6512688 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0141. Min Act: -0.1700
Data Index: 3053608 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1316. Min Range: -2.1316
Max Act: 2.0141. Min Act: -0.1700
Data Index: 8114346 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19