Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.9444. Min Act: -0.1700
Data Index: 2425951 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.9444. Min Act: -0.1700
Data Index: 2094322 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.6319. Min Act: -0.1700
Data Index: 365171 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.5694. Min Act: -0.1700
Data Index: 7804253 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.5069. Min Act: -0.1700
Data Index: 1027063 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.5069. Min Act: -0.1700
Data Index: 2986774 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.4444. Min Act: -0.1700
Data Index: 6914682 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.4444. Min Act: -0.1700
Data Index: 2717839 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.4444. Min Act: -0.1700
Data Index: 54578 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3819. Min Act: -0.1700
Data Index: 4250869 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3819. Min Act: -0.1700
Data Index: 3411355 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3819. Min Act: -0.1700
Data Index: 5786993 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3194. Min Act: -0.1700
Data Index: 143845 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3194. Min Act: -0.1700
Data Index: 6634139 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3194. Min Act: -0.1700
Data Index: 3545951 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3194. Min Act: -0.1700
Data Index: 6839907 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3819. Min Act: -0.1700
Data Index: 6531495 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3194. Min Act: -0.1700
Data Index: 5694023 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3194. Min Act: -0.1700
Data Index: 3978283 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9444. Min Range: -8.9444
Max Act: 8.3194. Min Act: -0.1700
Data Index: 3462836 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19