Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5322 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1214. Min Range: -5.1214
Max Act: 5.1214. Min Act: -0.1700
Data Index: 190804 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.8402. Min Act: -0.1700
Data Index: 190805 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.8402. Min Act: -0.1700
Data Index: 5791040 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.8089. Min Act: -0.1700
Data Index: 5791039 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.7152. Min Act: -0.1700
Data Index: 462738 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.6214. Min Act: -0.1700
Data Index: 7973751 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.6214. Min Act: -0.1700
Data Index: 1536179 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.5902. Min Act: -0.1700
Data Index: 1031625 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.5902. Min Act: -0.1700
Data Index: 7531187 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.5277. Min Act: -0.1700
Data Index: 2540053 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.4652. Min Act: -0.1700
Data Index: 8027328 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.4339. Min Act: -0.1700
Data Index: 1861689 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.4339. Min Act: -0.1700
Data Index: 2295240 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.4339. Min Act: -0.1700
Data Index: 5229196 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.4027. Min Act: -0.1700
Data Index: 4315746 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.4027. Min Act: -0.1700
Data Index: 6804615 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.4027. Min Act: -0.1700
Data Index: 4510661 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.3714. Min Act: -0.1700
Data Index: 359365 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.3714. Min Act: -0.1700
Data Index: 5651872 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1214. Min Range: -5.1214
Max Act: 4.3714. Min Act: -0.1700
Data Index: 4371908 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19