Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1203 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.4904. Min Act: -0.1700
Data Index: 8642562 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.3651. Min Act: -0.1700
Data Index: 8830645 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.3494. Min Act: -0.1700
Data Index: 1886852 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.3180. Min Act: -0.1700
Data Index: 8124213 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.2866. Min Act: -0.1700
Data Index: 491683 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.2080. Min Act: -0.1700
Data Index: 7729739 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.2237. Min Act: -0.1700
Data Index: 8633527 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.2395. Min Act: -0.1700
Data Index: 2330080 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.1923. Min Act: -0.1700
Data Index: 8752677 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.1608. Min Act: -0.1700
Data Index: 3934943 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.1451. Min Act: -0.1700
Data Index: 5129611 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.1293. Min Act: -0.1700
Data Index: 4312183 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.1293. Min Act: -0.1700
Data Index: 4321632 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.0978. Min Act: -0.1700
Data Index: 3826499 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.1293. Min Act: -0.1700
Data Index: 7098978 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.1136. Min Act: -0.1700
Data Index: 1072747 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.1136. Min Act: -0.1700
Data Index: 4976907 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.0978. Min Act: -0.1700
Data Index: 4423241 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.0978. Min Act: -0.1700
Data Index: 1503501 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4904. Min Range: -3.4904
Max Act: 3.0821. Min Act: -0.1700
Data Index: 4310892 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19