Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1430 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0650. Min Act: -0.1700
Data Index: 940445 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0650. Min Act: -0.1700
Data Index: 8507158 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0337. Min Act: -0.1700
Data Index: 7351835 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 1822798 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9087. Min Act: -0.1700
Data Index: 5584667 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8775. Min Act: -0.1700
Data Index: 4083775 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8775. Min Act: -0.1700
Data Index: 273843 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8462. Min Act: -0.1700
Data Index: 8747315 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 1517914 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 5608848 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 4276252 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7837. Min Act: -0.1700
Data Index: 6096804 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7525. Min Act: -0.1700
Data Index: 6207673 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7525. Min Act: -0.1700
Data Index: 2006278 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7525. Min Act: -0.1700
Data Index: 8389342 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7525. Min Act: -0.1700
Data Index: 2309877 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7212. Min Act: -0.1700
Data Index: 4419252 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7525. Min Act: -0.1700
Data Index: 1042321 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7525. Min Act: -0.1700
Data Index: 1925126 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.7525. Min Act: -0.1700
Data Index: 2562677 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19