Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.9936. Min Act: -0.1700
Data Index: 7123314 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.8061. Min Act: -0.1700
Data Index: 2236456 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.7749. Min Act: -0.1700
Data Index: 7021999 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.7436. Min Act: -0.1700
Data Index: 5683163 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.7124. Min Act: -0.1700
Data Index: 449609 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.6811. Min Act: -0.1700
Data Index: 6137954 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.6499. Min Act: -0.1700
Data Index: 6261089 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.6186. Min Act: -0.1700
Data Index: 285577 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.5874. Min Act: -0.1700
Data Index: 3506520 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.5874. Min Act: -0.1700
Data Index: 3120838 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.5874. Min Act: -0.1700
Data Index: 2770616 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.5561. Min Act: -0.1700
Data Index: 8646929 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.5561. Min Act: -0.1700
Data Index: 5442833 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.5561. Min Act: -0.1700
Data Index: 8353508 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.5249. Min Act: -0.1700
Data Index: 4442467 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.5561. Min Act: -0.1700
Data Index: 4363187 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.5249. Min Act: -0.1700
Data Index: 3199518 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.5249. Min Act: -0.1700
Data Index: 7041950 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.4624. Min Act: -0.1700
Data Index: 1849150 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9936. Min Range: -5.9936
Max Act: 5.4936. Min Act: -0.1700
Data Index: 446672 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19