Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 749 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.4500. Min Act: -0.1700
Data Index: 1811404 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.2938. Min Act: -0.1700
Data Index: 3423379 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.1688. Min Act: -0.1700
Data Index: 5077716 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.1375. Min Act: -0.1700
Data Index: 3956646 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.1375. Min Act: -0.1700
Data Index: 3423380 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.1063. Min Act: -0.1700
Data Index: 6539888 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.0438. Min Act: -0.1700
Data Index: 3248580 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.0438. Min Act: -0.1700
Data Index: 3809481 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.0125. Min Act: -0.1700
Data Index: 2867501 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.0125. Min Act: -0.1700
Data Index: 2316892 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4500. Min Range: -5.4500
Max Act: 5.0125. Min Act: -0.1700
Data Index: 5570235 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4500. Min Range: -5.4500
Max Act: 4.9813. Min Act: -0.1700
Data Index: 327740 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4500. Min Range: -5.4500
Max Act: 4.9813. Min Act: -0.1700
Data Index: 5503514 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4500. Min Range: -5.4500
Max Act: 4.9813. Min Act: -0.1700
Data Index: 8065537 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4500. Min Range: -5.4500
Max Act: 4.9813. Min Act: -0.1700
Data Index: 6828434 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4500. Min Range: -5.4500
Max Act: 4.9500. Min Act: -0.1700
Data Index: 4773448 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4500. Min Range: -5.4500
Max Act: 4.9500. Min Act: -0.1700
Data Index: 7128864 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4500. Min Range: -5.4500
Max Act: 4.9500. Min Act: -0.1700
Data Index: 5140937 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4500. Min Range: -5.4500
Max Act: 4.9500. Min Act: -0.1700
Data Index: 5018431 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4500. Min Range: -5.4500
Max Act: 4.9188. Min Act: -0.1700
Data Index: 6218367 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19