Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1781 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.3430. Min Act: -0.1700
Data Index: 6211124 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.2645. Min Act: -0.1700
Data Index: 4752939 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.2488. Min Act: -0.1700
Data Index: 4210157 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.2174. Min Act: -0.1700
Data Index: 6110497 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.2174. Min Act: -0.1700
Data Index: 7782896 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.1859. Min Act: -0.1700
Data Index: 8799017 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.1545. Min Act: -0.1700
Data Index: 2205609 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.1387. Min Act: -0.1700
Data Index: 6396705 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.1072. Min Act: -0.1700
Data Index: 4785453 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0441. Min Act: -0.1700
Data Index: 794251 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0757. Min Act: -0.1700
Data Index: 1876297 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0441. Min Act: -0.1700
Data Index: 6211123 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0441. Min Act: -0.1700
Data Index: 2058403 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0283. Min Act: -0.1700
Data Index: 7737255 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0441. Min Act: -0.1700
Data Index: 2434938 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0126. Min Act: -0.1700
Data Index: 4117234 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0283. Min Act: -0.1700
Data Index: 4984373 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0126. Min Act: -0.1700
Data Index: 2701209 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0126. Min Act: -0.1700
Data Index: 1508794 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3430. Min Range: -3.3430
Max Act: 3.0126. Min Act: -0.1700
Data Index: 6942056 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19