Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 621 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.6421. Min Act: -0.1700
Data Index: 5263837 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4970. Min Act: -0.1700
Data Index: 7072078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4970. Min Act: -0.1700
Data Index: 6419568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.5132. Min Act: -0.1700
Data Index: 1754168 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4970. Min Act: -0.1700
Data Index: 3977968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4970. Min Act: -0.1700
Data Index: 7061385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.5132. Min Act: -0.1700
Data Index: 4131909 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4970. Min Act: -0.1700
Data Index: 4101146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4970. Min Act: -0.1700
Data Index: 1126608 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4970. Min Act: -0.1700
Data Index: 1383019 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4970. Min Act: -0.1700
Data Index: 7136742 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4807. Min Act: -0.1700
Data Index: 362018 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4807. Min Act: -0.1700
Data Index: 4171576 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4645. Min Act: -0.1700
Data Index: 47511 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4645. Min Act: -0.1700
Data Index: 3878797 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4483. Min Act: -0.1700
Data Index: 3774472 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4320. Min Act: -0.1700
Data Index: 804277 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4320. Min Act: -0.1700
Data Index: 799843 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4320. Min Act: -0.1700
Data Index: 1496987 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6421. Min Range: -2.6421
Max Act: 2.4320. Min Act: -0.1700
Data Index: 4733046 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19