Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.8917. Min Act: -0.1700
Data Index: 8207198 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.5792. Min Act: -0.1700
Data Index: 2621564 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.5167. Min Act: -0.1700
Data Index: 4781135 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.4542. Min Act: -0.1700
Data Index: 6609151 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.3604. Min Act: -0.1700
Data Index: 5099289 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.2979. Min Act: -0.1700
Data Index: 2773807 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.2979. Min Act: -0.1700
Data Index: 2194355 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.2667. Min Act: -0.1700
Data Index: 1500710 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.2667. Min Act: -0.1700
Data Index: 1149348 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.2042. Min Act: -0.1700
Data Index: 5179623 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.2042. Min Act: -0.1700
Data Index: 6797528 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.2354. Min Act: -0.1700
Data Index: 662939 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.1729. Min Act: -0.1700
Data Index: 2192859 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.1417. Min Act: -0.1700
Data Index: 379555 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.1729. Min Act: -0.1700
Data Index: 2686084 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.1417. Min Act: -0.1700
Data Index: 2019645 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.1417. Min Act: -0.1700
Data Index: 5963870 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.1104. Min Act: -0.1700
Data Index: 1273883 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.0792. Min Act: -0.1700
Data Index: 4487259 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8917. Min Range: -5.8917
Max Act: 5.0792. Min Act: -0.1700
Data Index: 2537682 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19