Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0544. Min Range: -9.0544
Max Act: 9.0544. Min Act: -0.1700
Data Index: 834944 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.8669. Min Act: -0.1700
Data Index: 2154800 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.8044. Min Act: -0.1700
Data Index: 284125 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.4294. Min Act: -0.1700
Data Index: 2460744 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.4294. Min Act: -0.1700
Data Index: 8450783 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.3669. Min Act: -0.1700
Data Index: 2045149 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.3357. Min Act: -0.1700
Data Index: 6055243 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.3357. Min Act: -0.1700
Data Index: 7697832 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.2732. Min Act: -0.1700
Data Index: 6270631 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.2419. Min Act: -0.1700
Data Index: 5725995 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.2107. Min Act: -0.1700
Data Index: 32953 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.2107. Min Act: -0.1700
Data Index: 4750056 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.2107. Min Act: -0.1700
Data Index: 3405643 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.2107. Min Act: -0.1700
Data Index: 5182583 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.1482. Min Act: -0.1700
Data Index: 8493876 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.2107. Min Act: -0.1700
Data Index: 8562163 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.1482. Min Act: -0.1700
Data Index: 6250160 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.1169. Min Act: -0.1700
Data Index: 2581791 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0544. Min Range: -9.0544
Max Act: 8.0544. Min Act: -0.1700
Data Index: 5381354 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0544. Min Range: -9.0544
Max Act: 7.9919. Min Act: -0.1700
Data Index: 1547240 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19