Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4221 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.6732. Min Act: -0.1700
Data Index: 3246156 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.6732. Min Act: -0.1700
Data Index: 6237421 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.5795. Min Act: -0.1700
Data Index: 2668084 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.5482. Min Act: -0.1700
Data Index: 7970468 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.3295. Min Act: -0.1700
Data Index: 8037128 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.3295. Min Act: -0.1700
Data Index: 7621464 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.1732. Min Act: -0.1700
Data Index: 1889711 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.0795. Min Act: -0.1700
Data Index: 7429183 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.1107. Min Act: -0.1700
Data Index: 5165229 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.1107. Min Act: -0.1700
Data Index: 956166 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.0795. Min Act: -0.1700
Data Index: 2236763 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.0482. Min Act: -0.1700
Data Index: 2297523 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6732. Min Range: -7.6732
Max Act: 7.0482. Min Act: -0.1700
Data Index: 6260841 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6732. Min Range: -7.6732
Max Act: 6.9857. Min Act: -0.1700
Data Index: 4735176 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6732. Min Range: -7.6732
Max Act: 6.9857. Min Act: -0.1700
Data Index: 3104611 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6732. Min Range: -7.6732
Max Act: 6.9545. Min Act: -0.1700
Data Index: 5983280 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6732. Min Range: -7.6732
Max Act: 6.9545. Min Act: -0.1700
Data Index: 1425974 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6732. Min Range: -7.6732
Max Act: 6.9545. Min Act: -0.1700
Data Index: 1327942 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6732. Min Range: -7.6732
Max Act: 6.9232. Min Act: -0.1700
Data Index: 3376912 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6732. Min Range: -7.6732
Max Act: 6.8920. Min Act: -0.1700
Data Index: 7210873 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19