Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4757 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0059. Min Range: -11.0059
Max Act: 11.0059. Min Act: -0.1700
Data Index: 6349850 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0059. Min Range: -11.0059
Max Act: 11.0059. Min Act: -0.1700
Data Index: 4045135 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0059. Min Range: -11.0059
Max Act: 11.0059. Min Act: -0.1700
Data Index: 5887862 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.8184. Min Act: -0.1700
Data Index: 521388 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.8184. Min Act: -0.1700
Data Index: 3070410 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.8184. Min Act: -0.1700
Data Index: 6182251 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.7559. Min Act: -0.1700
Data Index: 2104152 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.7559. Min Act: -0.1700
Data Index: 3603611 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.7559. Min Act: -0.1700
Data Index: 6698445 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6934. Min Act: -0.1700
Data Index: 6842943 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6934. Min Act: -0.1700
Data Index: 3119829 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6934. Min Act: -0.1700
Data Index: 6181383 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6934. Min Act: -0.1700
Data Index: 4642674 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6934. Min Act: -0.1700
Data Index: 2887237 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6934. Min Act: -0.1700
Data Index: 960504 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6934. Min Act: -0.1700
Data Index: 6337062 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6934. Min Act: -0.1700
Data Index: 5486149 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6934. Min Act: -0.1700
Data Index: 5211324 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6934. Min Act: -0.1700
Data Index: 4367214 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0059. Min Range: -11.0059
Max Act: 10.6309. Min Act: -0.1700
Data Index: 6024628 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19