Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.2616. Min Act: -0.1700
Data Index: 7852593 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1366. Min Act: -0.1700
Data Index: 4528748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1366. Min Act: -0.1700
Data Index: 569730 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1366. Min Act: -0.1700
Data Index: 2583978 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1366. Min Act: -0.1700
Data Index: 890489 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1054. Min Act: -0.1700
Data Index: 717293 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.1054. Min Act: -0.1700
Data Index: 2706220 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.0741. Min Act: -0.1700
Data Index: 2883756 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.0429. Min Act: -0.1700
Data Index: 5323850 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.0116. Min Act: -0.1700
Data Index: 4756231 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.0116. Min Act: -0.1700
Data Index: 1693367 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2616. Min Range: -5.2616
Max Act: 4.9804. Min Act: -0.1700
Data Index: 5338388 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2616. Min Range: -5.2616
Max Act: 4.9491. Min Act: -0.1700
Data Index: 8391434 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2616. Min Range: -5.2616
Max Act: 4.9804. Min Act: -0.1700
Data Index: 635659 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2616. Min Range: -5.2616
Max Act: 5.0116. Min Act: -0.1700
Data Index: 8536167 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2616. Min Range: -5.2616
Max Act: 4.9491. Min Act: -0.1700
Data Index: 3509483 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2616. Min Range: -5.2616
Max Act: 4.9491. Min Act: -0.1700
Data Index: 2308289 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2616. Min Range: -5.2616
Max Act: 4.9491. Min Act: -0.1700
Data Index: 1995822 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2616. Min Range: -5.2616
Max Act: 4.9179. Min Act: -0.1700
Data Index: 3478726 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2616. Min Range: -5.2616
Max Act: 4.9491. Min Act: -0.1700
Data Index: 1788602 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19