Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.3193. Min Act: -0.1700
Data Index: 1316804 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.2881. Min Act: -0.1700
Data Index: 8600077 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.2568. Min Act: -0.1700
Data Index: 5490543 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.2881. Min Act: -0.1700
Data Index: 2106616 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.2568. Min Act: -0.1700
Data Index: 5254577 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.2568. Min Act: -0.1700
Data Index: 6837929 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.2256. Min Act: -0.1700
Data Index: 3793760 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.2256. Min Act: -0.1700
Data Index: 7080249 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.2256. Min Act: -0.1700
Data Index: 6834637 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1943. Min Act: -0.1700
Data Index: 6073934 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1631. Min Act: -0.1700
Data Index: 5676708 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1631. Min Act: -0.1700
Data Index: 1703219 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1631. Min Act: -0.1700
Data Index: 7286896 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1318. Min Act: -0.1700
Data Index: 3293073 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1318. Min Act: -0.1700
Data Index: 1815556 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1631. Min Act: -0.1700
Data Index: 2164151 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1318. Min Act: -0.1700
Data Index: 7103244 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1006. Min Act: -0.1700
Data Index: 1078682 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1006. Min Act: -0.1700
Data Index: 531699 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3193. Min Range: -5.3193
Max Act: 5.1006. Min Act: -0.1700
Data Index: 4440922 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19