Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.8961. Min Act: -0.1700
Data Index: 1778767 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.8336. Min Act: -0.1700
Data Index: 8239009 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.6149. Min Act: -0.1700
Data Index: 3088569 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.5524. Min Act: -0.1700
Data Index: 2435322 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.4586. Min Act: -0.1700
Data Index: 1380087 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.4274. Min Act: -0.1700
Data Index: 5157894 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.3961. Min Act: -0.1700
Data Index: 5113874 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.3961. Min Act: -0.1700
Data Index: 1805427 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.3649. Min Act: -0.1700
Data Index: 6522310 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.3649. Min Act: -0.1700
Data Index: 2268822 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.3024. Min Act: -0.1700
Data Index: 5435048 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.3024. Min Act: -0.1700
Data Index: 3691889 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.2711. Min Act: -0.1700
Data Index: 8627973 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.2711. Min Act: -0.1700
Data Index: 7212462 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.2399. Min Act: -0.1700
Data Index: 3769907 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.2399. Min Act: -0.1700
Data Index: 4280966 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.2399. Min Act: -0.1700
Data Index: 6044634 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.2086. Min Act: -0.1700
Data Index: 3885053 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.2399. Min Act: -0.1700
Data Index: 2098003 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8961. Min Range: -6.8961
Max Act: 6.2399. Min Act: -0.1700
Data Index: 5490367 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19