Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0343. Min Range: -4.0343
Max Act: 4.0343. Min Act: -0.1700
Data Index: 7081230 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.9718. Min Act: -0.1700
Data Index: 6384094 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.9405. Min Act: -0.1700
Data Index: 6811574 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.9405. Min Act: -0.1700
Data Index: 7709341 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.9405. Min Act: -0.1700
Data Index: 2602216 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 6371789 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.9093. Min Act: -0.1700
Data Index: 8511727 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 5032274 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8467. Min Act: -0.1700
Data Index: 6371791 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 5752543 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 3882923 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 7964901 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 860365 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 7826607 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 5186386 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 8156019 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8467. Min Act: -0.1700
Data Index: 8156020 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8467. Min Act: -0.1700
Data Index: 2253235 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8467. Min Act: -0.1700
Data Index: 8146385 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0343. Min Range: -4.0343
Max Act: 3.8780. Min Act: -0.1700
Data Index: 2388040 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19