Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1272 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2803. Min Range: -6.2803
Max Act: 6.2803. Min Act: -0.1700
Data Index: 7054647 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.7178. Min Act: -0.1700
Data Index: 1724449 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.6241. Min Act: -0.1700
Data Index: 2462838 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.6241. Min Act: -0.1700
Data Index: 2026984 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.5928. Min Act: -0.1700
Data Index: 68443 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.4991. Min Act: -0.1700
Data Index: 6275138 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.4053. Min Act: -0.1700
Data Index: 7941479 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.3428. Min Act: -0.1700
Data Index: 6980840 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.3116. Min Act: -0.1700
Data Index: 2443502 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.2803. Min Act: -0.1700
Data Index: 5175355 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.2491. Min Act: -0.1700
Data Index: 6632150 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.2803. Min Act: -0.1700
Data Index: 6708845 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.3116. Min Act: -0.1700
Data Index: 7846448 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.2803. Min Act: -0.1700
Data Index: 6472662 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.2491. Min Act: -0.1700
Data Index: 2073463 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.1866. Min Act: -0.1700
Data Index: 1666019 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.1866. Min Act: -0.1700
Data Index: 3420344 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.2178. Min Act: -0.1700
Data Index: 8493217 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.1866. Min Act: -0.1700
Data Index: 5175356 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2803. Min Range: -6.2803
Max Act: 5.1866. Min Act: -0.1700
Data Index: 2924457 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19