Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.6665. Min Act: -0.1700
Data Index: 8554794 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.6352. Min Act: -0.1700
Data Index: 1118151 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.2915. Min Act: -0.1700
Data Index: 3247416 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.2290. Min Act: -0.1700
Data Index: 592473 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.2290. Min Act: -0.1700
Data Index: 669958 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.1977. Min Act: -0.1700
Data Index: 7358031 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.2290. Min Act: -0.1700
Data Index: 1708478 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.1665. Min Act: -0.1700
Data Index: 4934524 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.1352. Min Act: -0.1700
Data Index: 2413915 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.1352. Min Act: -0.1700
Data Index: 2808004 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.1040. Min Act: -0.1700
Data Index: 2442608 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.1040. Min Act: -0.1700
Data Index: 8244796 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.1040. Min Act: -0.1700
Data Index: 7331633 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.1040. Min Act: -0.1700
Data Index: 8682660 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.0727. Min Act: -0.1700
Data Index: 590518 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.0727. Min Act: -0.1700
Data Index: 4645233 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.0727. Min Act: -0.1700
Data Index: 1464290 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.0415. Min Act: -0.1700
Data Index: 5209086 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.0727. Min Act: -0.1700
Data Index: 984495 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6665. Min Range: -5.6665
Max Act: 5.0415. Min Act: -0.1700
Data Index: 1152989 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19