Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1183. Min Range: -7.1183
Max Act: 7.1183. Min Act: -0.1700
Data Index: 5850921 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1183. Min Range: -7.1183
Max Act: 7.0871. Min Act: -0.1700
Data Index: 6184930 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.9933. Min Act: -0.1700
Data Index: 7530955 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.9621. Min Act: -0.1700
Data Index: 698413 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.8683. Min Act: -0.1700
Data Index: 6906452 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.8058. Min Act: -0.1700
Data Index: 5507486 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.6496. Min Act: -0.1700
Data Index: 5351994 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.6183. Min Act: -0.1700
Data Index: 1358227 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.5871. Min Act: -0.1700
Data Index: 5046888 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.5558. Min Act: -0.1700
Data Index: 8300198 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.4933. Min Act: -0.1700
Data Index: 1557538 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.5246. Min Act: -0.1700
Data Index: 4298935 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.4933. Min Act: -0.1700
Data Index: 4519041 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.5246. Min Act: -0.1700
Data Index: 2382699 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.5558. Min Act: -0.1700
Data Index: 7267385 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.4933. Min Act: -0.1700
Data Index: 2956774 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.4621. Min Act: -0.1700
Data Index: 55564 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.4308. Min Act: -0.1700
Data Index: 7807006 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.4621. Min Act: -0.1700
Data Index: 1412128 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1183. Min Range: -7.1183
Max Act: 6.4621. Min Act: -0.1700
Data Index: 6134140 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19