Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1478. Min Range: -7.1478
Max Act: 7.1478. Min Act: -0.1700
Data Index: 5298131 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1478. Min Range: -7.1478
Max Act: 7.0540. Min Act: -0.1700
Data Index: 1512791 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.9915. Min Act: -0.1700
Data Index: 6086278 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.9603. Min Act: -0.1700
Data Index: 3204716 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.9290. Min Act: -0.1700
Data Index: 7196681 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.8978. Min Act: -0.1700
Data Index: 1816346 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.8665. Min Act: -0.1700
Data Index: 4665423 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.8353. Min Act: -0.1700
Data Index: 4734865 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.8040. Min Act: -0.1700
Data Index: 6485556 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.7728. Min Act: -0.1700
Data Index: 8091890 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.7728. Min Act: -0.1700
Data Index: 2648231 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.7728. Min Act: -0.1700
Data Index: 2051043 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.7728. Min Act: -0.1700
Data Index: 8426507 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.7103. Min Act: -0.1700
Data Index: 6611570 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.7103. Min Act: -0.1700
Data Index: 279687 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.7103. Min Act: -0.1700
Data Index: 8168431 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.7103. Min Act: -0.1700
Data Index: 2617897 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.7103. Min Act: -0.1700
Data Index: 3213591 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.6790. Min Act: -0.1700
Data Index: 238181 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1478. Min Range: -7.1478
Max Act: 6.6478. Min Act: -0.1700
Data Index: 1534039 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19