Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.4616. Min Act: -0.1700
Data Index: 2669747 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.4303. Min Act: -0.1700
Data Index: 8761364 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.3678. Min Act: -0.1700
Data Index: 5022508 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.3366. Min Act: -0.1700
Data Index: 2834933 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.3366. Min Act: -0.1700
Data Index: 4976254 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.3053. Min Act: -0.1700
Data Index: 3392675 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.3053. Min Act: -0.1700
Data Index: 133966 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.2428. Min Act: -0.1700
Data Index: 7462991 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.2116. Min Act: -0.1700
Data Index: 6321895 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.1803. Min Act: -0.1700
Data Index: 6508871 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.1491. Min Act: -0.1700
Data Index: 8332933 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.1491. Min Act: -0.1700
Data Index: 422618 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.1491. Min Act: -0.1700
Data Index: 4433195 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.1491. Min Act: -0.1700
Data Index: 5820550 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.1178. Min Act: -0.1700
Data Index: 3195915 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.1178. Min Act: -0.1700
Data Index: 2403320 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.1178. Min Act: -0.1700
Data Index: 3468105 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.0866. Min Act: -0.1700
Data Index: 1344348 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.0866. Min Act: -0.1700
Data Index: 6933678 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4616. Min Range: -5.4616
Max Act: 5.0553. Min Act: -0.1700
Data Index: 2350662 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19