Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1723 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2046. Min Act: -0.1700
Data Index: 2485500 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2359. Min Act: -0.1700
Data Index: 7681205 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2046. Min Act: -0.1700
Data Index: 3178165 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1734. Min Act: -0.1700
Data Index: 7603877 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1734. Min Act: -0.1700
Data Index: 2359472 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1421. Min Act: -0.1700
Data Index: 4293950 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1421. Min Act: -0.1700
Data Index: 4379827 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1109. Min Act: -0.1700
Data Index: 5272271 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.0796. Min Act: -0.1700
Data Index: 7423242 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1109. Min Act: -0.1700
Data Index: 4550488 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1109. Min Act: -0.1700
Data Index: 3886684 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1109. Min Act: -0.1700
Data Index: 4180652 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1109. Min Act: -0.1700
Data Index: 5631489 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.0796. Min Act: -0.1700
Data Index: 2089248 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.0796. Min Act: -0.1700
Data Index: 6326542 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.0796. Min Act: -0.1700
Data Index: 3984344 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.0484. Min Act: -0.1700
Data Index: 2834636 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.0796. Min Act: -0.1700
Data Index: 2312479 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.0796. Min Act: -0.1700
Data Index: 4180646 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.0796. Min Act: -0.1700
Data Index: 3139722 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19