Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4774 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4525. Min Range: -9.4525
Max Act: 9.4525. Min Act: -0.1700
Data Index: 5060587 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4525. Min Range: -9.4525
Max Act: 9.3900. Min Act: -0.1700
Data Index: 309753 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4525. Min Range: -9.4525
Max Act: 9.3275. Min Act: -0.1700
Data Index: 6277019 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4525. Min Range: -9.4525
Max Act: 9.2025. Min Act: -0.1700
Data Index: 5336806 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4525. Min Range: -9.4525
Max Act: 9.1400. Min Act: -0.1700
Data Index: 7067508 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4525. Min Range: -9.4525
Max Act: 9.0150. Min Act: -0.1700
Data Index: 1532405 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4525. Min Range: -9.4525
Max Act: 9.0150. Min Act: -0.1700
Data Index: 4629083 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4525. Min Range: -9.4525
Max Act: 9.0150. Min Act: -0.1700
Data Index: 3663881 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.8900. Min Act: -0.1700
Data Index: 1836173 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.8900. Min Act: -0.1700
Data Index: 3457877 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.8900. Min Act: -0.1700
Data Index: 4518424 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.8900. Min Act: -0.1700
Data Index: 2281618 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.8900. Min Act: -0.1700
Data Index: 6716589 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.8275. Min Act: -0.1700
Data Index: 8203383 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.8275. Min Act: -0.1700
Data Index: 8813815 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.7650. Min Act: -0.1700
Data Index: 1149906 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.7650. Min Act: -0.1700
Data Index: 6605754 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.7650. Min Act: -0.1700
Data Index: 7613848 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.7650. Min Act: -0.1700
Data Index: 5776195 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4525. Min Range: -9.4525
Max Act: 8.7025. Min Act: -0.1700
Data Index: 1290878 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19