Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.6858. Min Act: -0.1700
Data Index: 8506675 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.6233. Min Act: -0.1700
Data Index: 1898056 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.5608. Min Act: -0.1700
Data Index: 7213386 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.5295. Min Act: -0.1700
Data Index: 2066936 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.5608. Min Act: -0.1700
Data Index: 7378157 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.4670. Min Act: -0.1700
Data Index: 6029520 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.4358. Min Act: -0.1700
Data Index: 7686964 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.3733. Min Act: -0.1700
Data Index: 4973856 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.3108. Min Act: -0.1700
Data Index: 8367231 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.2483. Min Act: -0.1700
Data Index: 30502 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.2483. Min Act: -0.1700
Data Index: 2718646 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.2483. Min Act: -0.1700
Data Index: 5679898 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.2170. Min Act: -0.1700
Data Index: 4801722 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.2170. Min Act: -0.1700
Data Index: 2716931 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.2170. Min Act: -0.1700
Data Index: 5058581 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.1858. Min Act: -0.1700
Data Index: 2077332 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.1545. Min Act: -0.1700
Data Index: 2463677 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.1545. Min Act: -0.1700
Data Index: 1522797 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.1545. Min Act: -0.1700
Data Index: 2908074 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6858. Min Range: -7.6858
Max Act: 7.1233. Min Act: -0.1700
Data Index: 1543442 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19