Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4111 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.7457. Min Act: -0.1700
Data Index: 4541992 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.6207. Min Act: -0.1700
Data Index: 7096973 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.5582. Min Act: -0.1700
Data Index: 7935088 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.4957. Min Act: -0.1700
Data Index: 70072 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.3707. Min Act: -0.1700
Data Index: 1841916 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.3707. Min Act: -0.1700
Data Index: 2023950 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.3082. Min Act: -0.1700
Data Index: 5100692 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.2457. Min Act: -0.1700
Data Index: 6454592 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.1832. Min Act: -0.1700
Data Index: 7327297 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.1832. Min Act: -0.1700
Data Index: 8593691 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.1832. Min Act: -0.1700
Data Index: 6725901 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.1832. Min Act: -0.1700
Data Index: 5707755 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.1207. Min Act: -0.1700
Data Index: 6287527 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.1207. Min Act: -0.1700
Data Index: 7745603 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.0582. Min Act: -0.1700
Data Index: 4508568 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.0582. Min Act: -0.1700
Data Index: 5288844 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.0582. Min Act: -0.1700
Data Index: 7903121 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.0582. Min Act: -0.1700
Data Index: 3889139 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.0582. Min Act: -0.1700
Data Index: 3786772 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7457. Min Range: -8.7457
Max Act: 8.0582. Min Act: -0.1700
Data Index: 5797452 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19