Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0739. Min Act: -0.1700
Data Index: 2962708 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0426. Min Act: -0.1700
Data Index: 3269006 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9801. Min Act: -0.1700
Data Index: 7532959 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9489. Min Act: -0.1700
Data Index: 606151 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8864. Min Act: -0.1700
Data Index: 2653385 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9176. Min Act: -0.1700
Data Index: 898318 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8864. Min Act: -0.1700
Data Index: 3979784 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8551. Min Act: -0.1700
Data Index: 8649026 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8864. Min Act: -0.1700
Data Index: 5610030 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8551. Min Act: -0.1700
Data Index: 5988651 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8239. Min Act: -0.1700
Data Index: 3352132 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7926. Min Act: -0.1700
Data Index: 6906490 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7926. Min Act: -0.1700
Data Index: 7395604 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7614. Min Act: -0.1700
Data Index: 2257791 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7614. Min Act: -0.1700
Data Index: 4293453 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7614. Min Act: -0.1700
Data Index: 5256452 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7301. Min Act: -0.1700
Data Index: 5938201 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6989. Min Act: -0.1700
Data Index: 6859078 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6989. Min Act: -0.1700
Data Index: 4161092 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6989. Min Act: -0.1700
Data Index: 4424226 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19