Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4049 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1740. Min Range: -5.1740
Max Act: 5.1740. Min Act: -0.1700
Data Index: 2194154 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1740. Min Range: -5.1740
Max Act: 5.1428. Min Act: -0.1700
Data Index: 4588633 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1740. Min Range: -5.1740
Max Act: 5.0178. Min Act: -0.1700
Data Index: 1154063 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1740. Min Range: -5.1740
Max Act: 5.0490. Min Act: -0.1700
Data Index: 2438323 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1740. Min Range: -5.1740
Max Act: 5.0490. Min Act: -0.1700
Data Index: 1596007 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.9865. Min Act: -0.1700
Data Index: 4903797 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1740. Min Range: -5.1740
Max Act: 5.0178. Min Act: -0.1700
Data Index: 6943212 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.9865. Min Act: -0.1700
Data Index: 773753 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.9553. Min Act: -0.1700
Data Index: 3232529 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.9865. Min Act: -0.1700
Data Index: 2027014 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.9240. Min Act: -0.1700
Data Index: 770287 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.8928. Min Act: -0.1700
Data Index: 117052 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.8615. Min Act: -0.1700
Data Index: 203896 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.8615. Min Act: -0.1700
Data Index: 5172107 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.8303. Min Act: -0.1700
Data Index: 2579657 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.8303. Min Act: -0.1700
Data Index: 7669088 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.8303. Min Act: -0.1700
Data Index: 1771024 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.8303. Min Act: -0.1700
Data Index: 2539128 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.8303. Min Act: -0.1700
Data Index: 1300457 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1740. Min Range: -5.1740
Max Act: 4.7990. Min Act: -0.1700
Data Index: 688220 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19