Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.9019. Min Act: -0.1700
Data Index: 8056233 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.8394. Min Act: -0.1700
Data Index: 7630366 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.7144. Min Act: -0.1700
Data Index: 4302713 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.6831. Min Act: -0.1700
Data Index: 425835 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.6831. Min Act: -0.1700
Data Index: 6337201 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.6206. Min Act: -0.1700
Data Index: 6861386 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.6519. Min Act: -0.1700
Data Index: 8181916 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.6519. Min Act: -0.1700
Data Index: 7392056 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.5894. Min Act: -0.1700
Data Index: 1430922 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.5581. Min Act: -0.1700
Data Index: 3714693 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.5269. Min Act: -0.1700
Data Index: 2168486 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.5269. Min Act: -0.1700
Data Index: 4936097 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.5269. Min Act: -0.1700
Data Index: 174272 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.4644. Min Act: -0.1700
Data Index: 4329761 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.5269. Min Act: -0.1700
Data Index: 4592543 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.4956. Min Act: -0.1700
Data Index: 5722847 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.4956. Min Act: -0.1700
Data Index: 1878059 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.4956. Min Act: -0.1700
Data Index: 7333732 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.4644. Min Act: -0.1700
Data Index: 2934950 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9019. Min Range: -5.9019
Max Act: 5.4644. Min Act: -0.1700
Data Index: 5603309 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19