Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4027 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.3268. Min Act: -0.1700
Data Index: 824059 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.1393. Min Act: -0.1700
Data Index: 3645980 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.1706. Min Act: -0.1700
Data Index: 4167877 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.1706. Min Act: -0.1700
Data Index: 4452201 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.1081. Min Act: -0.1700
Data Index: 1774559 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.0456. Min Act: -0.1700
Data Index: 8137432 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.0143. Min Act: -0.1700
Data Index: 4130355 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.9831. Min Act: -0.1700
Data Index: 8405943 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.0143. Min Act: -0.1700
Data Index: 1201379 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3268. Min Range: -6.3268
Max Act: 6.0143. Min Act: -0.1700
Data Index: 6461266 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8893. Min Act: -0.1700
Data Index: 4895455 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8893. Min Act: -0.1700
Data Index: 6335071 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8893. Min Act: -0.1700
Data Index: 8666163 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8893. Min Act: -0.1700
Data Index: 3730724 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8581. Min Act: -0.1700
Data Index: 3221704 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8581. Min Act: -0.1700
Data Index: 1260004 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8893. Min Act: -0.1700
Data Index: 3234247 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8581. Min Act: -0.1700
Data Index: 8484789 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8268. Min Act: -0.1700
Data Index: 4274158 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3268. Min Range: -6.3268
Max Act: 5.8268. Min Act: -0.1700
Data Index: 5790667 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19