Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1492 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7908. Min Act: -0.1700
Data Index: 99128 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7595. Min Act: -0.1700
Data Index: 5268522 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7282. Min Act: -0.1700
Data Index: 5932179 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7908. Min Act: -0.1700
Data Index: 1514182 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7282. Min Act: -0.1700
Data Index: 769996 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7282. Min Act: -0.1700
Data Index: 4795836 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.7126. Min Act: -0.1700
Data Index: 1629823 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6813. Min Act: -0.1700
Data Index: 5942719 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6656. Min Act: -0.1700
Data Index: 315813 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6343. Min Act: -0.1700
Data Index: 6340083 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6500. Min Act: -0.1700
Data Index: 5150872 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6656. Min Act: -0.1700
Data Index: 4795823 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6343. Min Act: -0.1700
Data Index: 227524 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6813. Min Act: -0.1700
Data Index: 6214090 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6030. Min Act: -0.1700
Data Index: 3514750 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6187. Min Act: -0.1700
Data Index: 6043632 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6343. Min Act: -0.1700
Data Index: 2806538 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6343. Min Act: -0.1700
Data Index: 1014659 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6030. Min Act: -0.1700
Data Index: 2200296 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7908. Min Range: -3.7908
Max Act: 3.6030. Min Act: -0.1700
Data Index: 509109 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19