Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2063 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.5593. Min Act: -0.1700
Data Index: 4332198 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.5593. Min Act: -0.1700
Data Index: 8621203 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.4654. Min Act: -0.1700
Data Index: 8392343 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.4340. Min Act: -0.1700
Data Index: 4878601 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.3870. Min Act: -0.1700
Data Index: 4538676 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.3870. Min Act: -0.1700
Data Index: 8247851 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.3556. Min Act: -0.1700
Data Index: 4045096 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.3242. Min Act: -0.1700
Data Index: 3455936 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.3399. Min Act: -0.1700
Data Index: 245981 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.2614. Min Act: -0.1700
Data Index: 6778446 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.2771. Min Act: -0.1700
Data Index: 3020815 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.2143. Min Act: -0.1700
Data Index: 5810080 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.2300. Min Act: -0.1700
Data Index: 8042479 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.2143. Min Act: -0.1700
Data Index: 3499660 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.2300. Min Act: -0.1700
Data Index: 1778317 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.2143. Min Act: -0.1700
Data Index: 1444725 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.1986. Min Act: -0.1700
Data Index: 8390020 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.1986. Min Act: -0.1700
Data Index: 768596 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.1671. Min Act: -0.1700
Data Index: 8254430 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5593. Min Range: -3.5593
Max Act: 3.1828. Min Act: -0.1700
Data Index: 7186137 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19