Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1375 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0404. Min Range: -3.0404
Max Act: 3.0404. Min Act: -0.1700
Data Index: 280389 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0404. Min Range: -3.0404
Max Act: 3.0088. Min Act: -0.1700
Data Index: 3726961 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.9614. Min Act: -0.1700
Data Index: 1328519 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.9456. Min Act: -0.1700
Data Index: 1775562 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.9456. Min Act: -0.1700
Data Index: 4694155 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.9456. Min Act: -0.1700
Data Index: 5121505 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.9297. Min Act: -0.1700
Data Index: 3023114 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.9139. Min Act: -0.1700
Data Index: 8687352 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.9139. Min Act: -0.1700
Data Index: 8393124 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.9139. Min Act: -0.1700
Data Index: 2745687 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.8980. Min Act: -0.1700
Data Index: 7680846 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.8980. Min Act: -0.1700
Data Index: 7786270 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.8980. Min Act: -0.1700
Data Index: 392238 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.8980. Min Act: -0.1700
Data Index: 4602657 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.8980. Min Act: -0.1700
Data Index: 7705273 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.8980. Min Act: -0.1700
Data Index: 8471429 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.8980. Min Act: -0.1700
Data Index: 8364239 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.8663. Min Act: -0.1700
Data Index: 894651 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.8663. Min Act: -0.1700
Data Index: 5672478 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0404. Min Range: -3.0404
Max Act: 2.8980. Min Act: -0.1700
Data Index: 5459395 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19