Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4013 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0159. Min Range: -4.0159
Max Act: 4.0159. Min Act: -0.1700
Data Index: 3856928 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.9846. Min Act: -0.1700
Data Index: 6394329 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.9221. Min Act: -0.1700
Data Index: 6465470 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.8908. Min Act: -0.1700
Data Index: 1468511 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.8595. Min Act: -0.1700
Data Index: 2592459 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.8283. Min Act: -0.1700
Data Index: 2199689 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.8283. Min Act: -0.1700
Data Index: 7238947 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7970. Min Act: -0.1700
Data Index: 4730530 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.8283. Min Act: -0.1700
Data Index: 7983048 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7970. Min Act: -0.1700
Data Index: 5524215 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7970. Min Act: -0.1700
Data Index: 6986572 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7657. Min Act: -0.1700
Data Index: 1943277 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7344. Min Act: -0.1700
Data Index: 8669135 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7344. Min Act: -0.1700
Data Index: 6472531 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7344. Min Act: -0.1700
Data Index: 1394032 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7344. Min Act: -0.1700
Data Index: 5983453 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7344. Min Act: -0.1700
Data Index: 5470808 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7344. Min Act: -0.1700
Data Index: 8035562 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7032. Min Act: -0.1700
Data Index: 4913597 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0159. Min Range: -4.0159
Max Act: 3.7032. Min Act: -0.1700
Data Index: 3478661 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19