Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.8917. Min Act: -0.1700
Data Index: 927925 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.8917. Min Act: -0.1700
Data Index: 5978671 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.8292. Min Act: -0.1700
Data Index: 2585162 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.8292. Min Act: -0.1700
Data Index: 2244845 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.8292. Min Act: -0.1700
Data Index: 1870507 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.8292. Min Act: -0.1700
Data Index: 6058161 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7979. Min Act: -0.1700
Data Index: 4561323 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7667. Min Act: -0.1700
Data Index: 767169 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7667. Min Act: -0.1700
Data Index: 4905057 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7667. Min Act: -0.1700
Data Index: 971968 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7667. Min Act: -0.1700
Data Index: 1061177 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7667. Min Act: -0.1700
Data Index: 2204892 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7354. Min Act: -0.1700
Data Index: 6768502 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7354. Min Act: -0.1700
Data Index: 4758619 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7354. Min Act: -0.1700
Data Index: 6757359 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7354. Min Act: -0.1700
Data Index: 2392943 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7354. Min Act: -0.1700
Data Index: 25987 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7354. Min Act: -0.1700
Data Index: 8242826 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7354. Min Act: -0.1700
Data Index: 1686465 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8917. Min Range: -4.8917
Max Act: 4.7354. Min Act: -0.1700
Data Index: 8750230 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19