Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3459 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2526. Min Range: -7.2526
Max Act: 7.2526. Min Act: -0.1700
Data Index: 1352681 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2526. Min Range: -7.2526
Max Act: 7.1276. Min Act: -0.1700
Data Index: 8121769 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2526. Min Range: -7.2526
Max Act: 7.1276. Min Act: -0.1700
Data Index: 933284 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2526. Min Range: -7.2526
Max Act: 7.0026. Min Act: -0.1700
Data Index: 5072908 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.9401. Min Act: -0.1700
Data Index: 6934051 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.9401. Min Act: -0.1700
Data Index: 3024742 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.8776. Min Act: -0.1700
Data Index: 5071022 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.8776. Min Act: -0.1700
Data Index: 5799551 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.8776. Min Act: -0.1700
Data Index: 2636039 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.8776. Min Act: -0.1700
Data Index: 5770691 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.8151. Min Act: -0.1700
Data Index: 3379139 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.8151. Min Act: -0.1700
Data Index: 2509989 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.8151. Min Act: -0.1700
Data Index: 7775839 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.8151. Min Act: -0.1700
Data Index: 8814962 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.8151. Min Act: -0.1700
Data Index: 7166573 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.7526. Min Act: -0.1700
Data Index: 3350778 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.7526. Min Act: -0.1700
Data Index: 1579491 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.7526. Min Act: -0.1700
Data Index: 1831597 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.7526. Min Act: -0.1700
Data Index: 2394777 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2526. Min Range: -7.2526
Max Act: 6.7526. Min Act: -0.1700
Data Index: 1098510 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19