Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.8088. Min Act: -0.1700
Data Index: 5186534 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.8088. Min Act: -0.1700
Data Index: 1117483 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.4963. Min Act: -0.1700
Data Index: 3802428 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.5276. Min Act: -0.1700
Data Index: 5055654 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.4963. Min Act: -0.1700
Data Index: 3320558 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.4963. Min Act: -0.1700
Data Index: 3898269 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.4338. Min Act: -0.1700
Data Index: 566484 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.4651. Min Act: -0.1700
Data Index: 89430 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.4338. Min Act: -0.1700
Data Index: 4008063 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.4338. Min Act: -0.1700
Data Index: 4379208 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.4026. Min Act: -0.1700
Data Index: 7693821 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.4026. Min Act: -0.1700
Data Index: 8540836 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.4026. Min Act: -0.1700
Data Index: 3671305 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.3713. Min Act: -0.1700
Data Index: 2468680 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.3713. Min Act: -0.1700
Data Index: 620781 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.3713. Min Act: -0.1700
Data Index: 8750559 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.3401. Min Act: -0.1700
Data Index: 4620633 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.3713. Min Act: -0.1700
Data Index: 1869812 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.3401. Min Act: -0.1700
Data Index: 3818112 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8088. Min Range: -5.8088
Max Act: 5.3088. Min Act: -0.1700
Data Index: 7078009 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19