Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1764 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2715. Min Range: -6.2715
Max Act: 6.2715. Min Act: -0.1700
Data Index: 2717460 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2715. Min Range: -6.2715
Max Act: 6.2090. Min Act: -0.1700
Data Index: 3090521 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2715. Min Range: -6.2715
Max Act: 6.0528. Min Act: -0.1700
Data Index: 19183 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2715. Min Range: -6.2715
Max Act: 6.0215. Min Act: -0.1700
Data Index: 1168231 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2715. Min Range: -6.2715
Max Act: 6.0215. Min Act: -0.1700
Data Index: 6650446 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2715. Min Range: -6.2715
Max Act: 6.0215. Min Act: -0.1700
Data Index: 4158971 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.9903. Min Act: -0.1700
Data Index: 5143152 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.9903. Min Act: -0.1700
Data Index: 3827644 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2715. Min Range: -6.2715
Max Act: 6.0215. Min Act: -0.1700
Data Index: 3893624 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.9590. Min Act: -0.1700
Data Index: 3644193 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.9590. Min Act: -0.1700
Data Index: 2098511 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.9590. Min Act: -0.1700
Data Index: 4273819 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.9278. Min Act: -0.1700
Data Index: 5410823 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.9278. Min Act: -0.1700
Data Index: 1973313 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.8965. Min Act: -0.1700
Data Index: 901781 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.8965. Min Act: -0.1700
Data Index: 4431228 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.8965. Min Act: -0.1700
Data Index: 2327726 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.8653. Min Act: -0.1700
Data Index: 79672 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.8340. Min Act: -0.1700
Data Index: 3550938 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2715. Min Range: -6.2715
Max Act: 5.8653. Min Act: -0.1700
Data Index: 6928282 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19