Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.9773. Min Act: -0.1700
Data Index: 8044842 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.8523. Min Act: -0.1700
Data Index: 150404 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.6648. Min Act: -0.1700
Data Index: 5533538 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.6023. Min Act: -0.1700
Data Index: 5965501 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.6023. Min Act: -0.1700
Data Index: 4595839 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.6023. Min Act: -0.1700
Data Index: 1622774 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.4773. Min Act: -0.1700
Data Index: 6808563 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.4773. Min Act: -0.1700
Data Index: 7759168 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.4773. Min Act: -0.1700
Data Index: 7782351 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.4148. Min Act: -0.1700
Data Index: 3437019 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.4148. Min Act: -0.1700
Data Index: 4288217 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.3523. Min Act: -0.1700
Data Index: 348514 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.3523. Min Act: -0.1700
Data Index: 7500629 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.3523. Min Act: -0.1700
Data Index: 5633881 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.3523. Min Act: -0.1700
Data Index: 3013342 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.2898. Min Act: -0.1700
Data Index: 464100 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.2273. Min Act: -0.1700
Data Index: 7902994 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.2273. Min Act: -0.1700
Data Index: 5007880 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.2273. Min Act: -0.1700
Data Index: 281601 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9773. Min Range: -8.9773
Max Act: 8.1648. Min Act: -0.1700
Data Index: 5634123 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19