Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5570 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.9318. Min Act: -0.1700
Data Index: 3175107 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.7755. Min Act: -0.1700
Data Index: 8459886 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.5568. Min Act: -0.1700
Data Index: 5102457 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.5255. Min Act: -0.1700
Data Index: 3568283 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.4630. Min Act: -0.1700
Data Index: 3406184 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.3693. Min Act: -0.1700
Data Index: 212539 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.4005. Min Act: -0.1700
Data Index: 3616029 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.3693. Min Act: -0.1700
Data Index: 6772377 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.3693. Min Act: -0.1700
Data Index: 5386590 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.3380. Min Act: -0.1700
Data Index: 612747 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.3380. Min Act: -0.1700
Data Index: 3641364 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.3380. Min Act: -0.1700
Data Index: 5198830 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.3068. Min Act: -0.1700
Data Index: 7259431 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.2755. Min Act: -0.1700
Data Index: 4927319 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.3068. Min Act: -0.1700
Data Index: 7339528 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.2755. Min Act: -0.1700
Data Index: 4474189 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.2755. Min Act: -0.1700
Data Index: 7241372 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.2443. Min Act: -0.1700
Data Index: 4942455 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.2130. Min Act: -0.1700
Data Index: 7556284 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9318. Min Range: -5.9318
Max Act: 5.2443. Min Act: -0.1700
Data Index: 4425858 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19