Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1999 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2033. Min Range: -7.2033
Max Act: 7.2033. Min Act: -0.1700
Data Index: 370430 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.9845. Min Act: -0.1700
Data Index: 3957330 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.8595. Min Act: -0.1700
Data Index: 4409880 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.7345. Min Act: -0.1700
Data Index: 2039679 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.7033. Min Act: -0.1700
Data Index: 8570048 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.6720. Min Act: -0.1700
Data Index: 6294777 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.7033. Min Act: -0.1700
Data Index: 5083770 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.7033. Min Act: -0.1700
Data Index: 6612668 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.6720. Min Act: -0.1700
Data Index: 8196236 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.6095. Min Act: -0.1700
Data Index: 2756372 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.6095. Min Act: -0.1700
Data Index: 873629 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.5783. Min Act: -0.1700
Data Index: 5319747 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.5783. Min Act: -0.1700
Data Index: 5817589 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.5470. Min Act: -0.1700
Data Index: 3215981 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.4845. Min Act: -0.1700
Data Index: 876341 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.4220. Min Act: -0.1700
Data Index: 3081901 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.4220. Min Act: -0.1700
Data Index: 4265370 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.3908. Min Act: -0.1700
Data Index: 6102955 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.3595. Min Act: -0.1700
Data Index: 414026 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2033. Min Range: -7.2033
Max Act: 6.3283. Min Act: -0.1700
Data Index: 2272678 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19