Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3075 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4662. Min Range: -7.4662
Max Act: 7.4662. Min Act: -0.1700
Data Index: 8166191 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4662. Min Range: -7.4662
Max Act: 7.0600. Min Act: -0.1700
Data Index: 7634247 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4662. Min Range: -7.4662
Max Act: 7.0287. Min Act: -0.1700
Data Index: 421316 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.9975. Min Act: -0.1700
Data Index: 1545633 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.8100. Min Act: -0.1700
Data Index: 356531 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.7787. Min Act: -0.1700
Data Index: 5263369 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.7475. Min Act: -0.1700
Data Index: 1068496 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.7787. Min Act: -0.1700
Data Index: 5119654 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.7475. Min Act: -0.1700
Data Index: 258340 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.7475. Min Act: -0.1700
Data Index: 6283202 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.6850. Min Act: -0.1700
Data Index: 761102 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.6537. Min Act: -0.1700
Data Index: 4394790 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.6537. Min Act: -0.1700
Data Index: 7110987 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.6537. Min Act: -0.1700
Data Index: 1523237 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.6225. Min Act: -0.1700
Data Index: 6314744 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.6537. Min Act: -0.1700
Data Index: 3838745 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.6225. Min Act: -0.1700
Data Index: 6050896 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.6225. Min Act: -0.1700
Data Index: 7061896 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.6225. Min Act: -0.1700
Data Index: 4401221 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4662. Min Range: -7.4662
Max Act: 6.5912. Min Act: -0.1700
Data Index: 1066060 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19