Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2644 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.8317. Min Act: -0.1700
Data Index: 5367436 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.6129. Min Act: -0.1700
Data Index: 6203030 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.5817. Min Act: -0.1700
Data Index: 1460417 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.5504. Min Act: -0.1700
Data Index: 2669523 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4879. Min Act: -0.1700
Data Index: 7988122 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4879. Min Act: -0.1700
Data Index: 8083313 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4879. Min Act: -0.1700
Data Index: 7050928 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4567. Min Act: -0.1700
Data Index: 4675042 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4567. Min Act: -0.1700
Data Index: 107232 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4879. Min Act: -0.1700
Data Index: 7880685 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4567. Min Act: -0.1700
Data Index: 239322 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4567. Min Act: -0.1700
Data Index: 959933 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4254. Min Act: -0.1700
Data Index: 963020 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4254. Min Act: -0.1700
Data Index: 5445359 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4254. Min Act: -0.1700
Data Index: 5218603 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.4254. Min Act: -0.1700
Data Index: 5890927 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.3942. Min Act: -0.1700
Data Index: 8085147 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.3942. Min Act: -0.1700
Data Index: 8303193 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.3629. Min Act: -0.1700
Data Index: 4099521 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8317. Min Range: -6.8317
Max Act: 6.3317. Min Act: -0.1700
Data Index: 5367433 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19