Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1652 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.6550. Min Act: -0.1700
Data Index: 1095 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.4988. Min Act: -0.1700
Data Index: 4224240 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.3738. Min Act: -0.1700
Data Index: 6497209 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.4050. Min Act: -0.1700
Data Index: 5575554 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.3113. Min Act: -0.1700
Data Index: 7709410 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.2488. Min Act: -0.1700
Data Index: 827728 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.2488. Min Act: -0.1700
Data Index: 4799639 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.2175. Min Act: -0.1700
Data Index: 992280 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.1863. Min Act: -0.1700
Data Index: 827727 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.1550. Min Act: -0.1700
Data Index: 6317261 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.1550. Min Act: -0.1700
Data Index: 7992792 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.1550. Min Act: -0.1700
Data Index: 6069507 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.1238. Min Act: -0.1700
Data Index: 8387008 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.1238. Min Act: -0.1700
Data Index: 2471503 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.0925. Min Act: -0.1700
Data Index: 962050 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.0613. Min Act: -0.1700
Data Index: 7991153 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.0613. Min Act: -0.1700
Data Index: 6144948 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.0613. Min Act: -0.1700
Data Index: 2153448 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.0613. Min Act: -0.1700
Data Index: 7635034 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6550. Min Range: -6.6550
Max Act: 6.0613. Min Act: -0.1700
Data Index: 6896915 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19