Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4830 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.8748. Min Act: -0.1700
Data Index: 5525305 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.7654. Min Act: -0.1700
Data Index: 4524167 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.7497. Min Act: -0.1700
Data Index: 3276835 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.7341. Min Act: -0.1700
Data Index: 2694837 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.7341. Min Act: -0.1700
Data Index: 8162811 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.7184. Min Act: -0.1700
Data Index: 6798558 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.6872. Min Act: -0.1700
Data Index: 3141016 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.6872. Min Act: -0.1700
Data Index: 705110 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.6715. Min Act: -0.1700
Data Index: 1804186 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.6089. Min Act: -0.1700
Data Index: 5391138 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.6246. Min Act: -0.1700
Data Index: 622745 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.6089. Min Act: -0.1700
Data Index: 5283971 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.6089. Min Act: -0.1700
Data Index: 2123070 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.6089. Min Act: -0.1700
Data Index: 6355932 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.6089. Min Act: -0.1700
Data Index: 946215 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.5933. Min Act: -0.1700
Data Index: 7167732 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.6089. Min Act: -0.1700
Data Index: 2573615 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.5933. Min Act: -0.1700
Data Index: 4421654 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.5776. Min Act: -0.1700
Data Index: 4066543 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8748. Min Range: -3.8748
Max Act: 3.5776. Min Act: -0.1700
Data Index: 5934456 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19