Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 485 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.6210. Min Act: -0.1700
Data Index: 4787872 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.5273. Min Act: -0.1700
Data Index: 2410553 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.5273. Min Act: -0.1700
Data Index: 2409778 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4960. Min Act: -0.1700
Data Index: 2196875 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4648. Min Act: -0.1700
Data Index: 7654082 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4648. Min Act: -0.1700
Data Index: 182808 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4023. Min Act: -0.1700
Data Index: 215684 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4335. Min Act: -0.1700
Data Index: 7247323 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4335. Min Act: -0.1700
Data Index: 2112953 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4023. Min Act: -0.1700
Data Index: 3814702 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4023. Min Act: -0.1700
Data Index: 164048 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4023. Min Act: -0.1700
Data Index: 7230225 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4023. Min Act: -0.1700
Data Index: 8574257 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4023. Min Act: -0.1700
Data Index: 7839732 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4023. Min Act: -0.1700
Data Index: 3457160 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4023. Min Act: -0.1700
Data Index: 4348788 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4023. Min Act: -0.1700
Data Index: 7620293 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.4335. Min Act: -0.1700
Data Index: 3875035 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.3398. Min Act: -0.1700
Data Index: 4386689 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6210. Min Range: -5.6210
Max Act: 5.3710. Min Act: -0.1700
Data Index: 3205036 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19