Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1230. Min Range: -6.1230
Max Act: 6.1230. Min Act: -0.1700
Data Index: 5777785 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.9355. Min Act: -0.1700
Data Index: 8242676 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.8730. Min Act: -0.1700
Data Index: 3067880 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.8417. Min Act: -0.1700
Data Index: 3512530 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.8105. Min Act: -0.1700
Data Index: 5417158 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.7480. Min Act: -0.1700
Data Index: 1212965 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.7480. Min Act: -0.1700
Data Index: 8120277 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.7167. Min Act: -0.1700
Data Index: 4401247 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6855. Min Act: -0.1700
Data Index: 5388500 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6855. Min Act: -0.1700
Data Index: 2981287 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6855. Min Act: -0.1700
Data Index: 3082597 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6855. Min Act: -0.1700
Data Index: 3286085 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6542. Min Act: -0.1700
Data Index: 2796556 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6542. Min Act: -0.1700
Data Index: 328340 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6542. Min Act: -0.1700
Data Index: 7535368 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6542. Min Act: -0.1700
Data Index: 2987575 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6542. Min Act: -0.1700
Data Index: 5845975 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6542. Min Act: -0.1700
Data Index: 3848266 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6230. Min Act: -0.1700
Data Index: 6349145 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1230. Min Range: -6.1230
Max Act: 5.6230. Min Act: -0.1700
Data Index: 7605555 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19