Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4363 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9605. Min Range: -7.9605
Max Act: 7.9605. Min Act: -0.1700
Data Index: 82487 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9605. Min Range: -7.9605
Max Act: 7.5542. Min Act: -0.1700
Data Index: 8812101 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9605. Min Range: -7.9605
Max Act: 7.2105. Min Act: -0.1700
Data Index: 884791 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9605. Min Range: -7.9605
Max Act: 7.1792. Min Act: -0.1700
Data Index: 1405761 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9605. Min Range: -7.9605
Max Act: 7.1792. Min Act: -0.1700
Data Index: 4768900 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9605. Min Range: -7.9605
Max Act: 7.1480. Min Act: -0.1700
Data Index: 3453528 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9605. Min Range: -7.9605
Max Act: 7.0855. Min Act: -0.1700
Data Index: 8482002 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9605. Min Range: -7.9605
Max Act: 7.0855. Min Act: -0.1700
Data Index: 150028 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9605. Min Range: -7.9605
Max Act: 7.0230. Min Act: -0.1700
Data Index: 4419152 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9605. Min Range: -7.9605
Max Act: 7.0230. Min Act: -0.1700
Data Index: 8573986 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9605. Min Range: -7.9605
Max Act: 6.9605. Min Act: -0.1700
Data Index: 1029466 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9605. Min Range: -7.9605
Max Act: 6.9292. Min Act: -0.1700
Data Index: 8063444 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9605. Min Range: -7.9605
Max Act: 6.8667. Min Act: -0.1700
Data Index: 7520479 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9605. Min Range: -7.9605
Max Act: 6.8980. Min Act: -0.1700
Data Index: 1112793 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9605. Min Range: -7.9605
Max Act: 6.8980. Min Act: -0.1700
Data Index: 2384064 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9605. Min Range: -7.9605
Max Act: 6.8980. Min Act: -0.1700
Data Index: 421162 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9605. Min Range: -7.9605
Max Act: 6.8980. Min Act: -0.1700
Data Index: 3398059 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9605. Min Range: -7.9605
Max Act: 6.8667. Min Act: -0.1700
Data Index: 5368127 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9605. Min Range: -7.9605
Max Act: 6.8667. Min Act: -0.1700
Data Index: 1723467 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9605. Min Range: -7.9605
Max Act: 6.8355. Min Act: -0.1700
Data Index: 6543613 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19