Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.5701. Min Act: -0.1700
Data Index: 5057317 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.5231. Min Act: -0.1700
Data Index: 6423325 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.4918. Min Act: -0.1700
Data Index: 852490 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.4918. Min Act: -0.1700
Data Index: 959227 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.4448. Min Act: -0.1700
Data Index: 5165260 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.4291. Min Act: -0.1700
Data Index: 7851350 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.4291. Min Act: -0.1700
Data Index: 6537802 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.4135. Min Act: -0.1700
Data Index: 4687793 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.4135. Min Act: -0.1700
Data Index: 959228 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.3978. Min Act: -0.1700
Data Index: 5369814 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.4135. Min Act: -0.1700
Data Index: 1053043 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.3664. Min Act: -0.1700
Data Index: 4469584 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.3664. Min Act: -0.1700
Data Index: 4595112 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.3507. Min Act: -0.1700
Data Index: 3608619 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.3821. Min Act: -0.1700
Data Index: 1239949 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.3350. Min Act: -0.1700
Data Index: 8255651 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.3350. Min Act: -0.1700
Data Index: 8189218 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.3350. Min Act: -0.1700
Data Index: 7069777 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.3507. Min Act: -0.1700
Data Index: 3017640 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5701. Min Range: -3.5701
Max Act: 3.3350. Min Act: -0.1700
Data Index: 8450543 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19