Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.1362. Min Act: -0.1700
Data Index: 2428369 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.1049. Min Act: -0.1700
Data Index: 1876074 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.0737. Min Act: -0.1700
Data Index: 3535156 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.0424. Min Act: -0.1700
Data Index: 1603019 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.0112. Min Act: -0.1700
Data Index: 2947452 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1362. Min Range: -4.1362
Max Act: 4.0112. Min Act: -0.1700
Data Index: 3270400 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9799. Min Act: -0.1700
Data Index: 816378 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9799. Min Act: -0.1700
Data Index: 5875597 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9486. Min Act: -0.1700
Data Index: 1876072 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9174. Min Act: -0.1700
Data Index: 83279 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9174. Min Act: -0.1700
Data Index: 8170184 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9174. Min Act: -0.1700
Data Index: 5433662 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9174. Min Act: -0.1700
Data Index: 8494084 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9174. Min Act: -0.1700
Data Index: 816380 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.8861. Min Act: -0.1700
Data Index: 1505891 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.8861. Min Act: -0.1700
Data Index: 6523178 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.8861. Min Act: -0.1700
Data Index: 6006648 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.8861. Min Act: -0.1700
Data Index: 2564550 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.9174. Min Act: -0.1700
Data Index: 1876073 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1362. Min Range: -4.1362
Max Act: 3.8861. Min Act: -0.1700
Data Index: 5151624 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19