Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4353 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.7860. Min Act: -0.1700
Data Index: 847311 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.7235. Min Act: -0.1700
Data Index: 379530 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.7235. Min Act: -0.1700
Data Index: 3469863 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.6923. Min Act: -0.1700
Data Index: 7004018 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.6298. Min Act: -0.1700
Data Index: 4867593 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.6298. Min Act: -0.1700
Data Index: 6305628 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.5985. Min Act: -0.1700
Data Index: 8515368 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.5985. Min Act: -0.1700
Data Index: 793031 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.5360. Min Act: -0.1700
Data Index: 4480564 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.5048. Min Act: -0.1700
Data Index: 7216139 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.5048. Min Act: -0.1700
Data Index: 380713 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.5048. Min Act: -0.1700
Data Index: 6654738 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.4735. Min Act: -0.1700
Data Index: 3257970 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.4735. Min Act: -0.1700
Data Index: 5478936 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.4423. Min Act: -0.1700
Data Index: 5688355 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.4110. Min Act: -0.1700
Data Index: 8523027 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.4423. Min Act: -0.1700
Data Index: 8706053 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.4423. Min Act: -0.1700
Data Index: 411031 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.4423. Min Act: -0.1700
Data Index: 2709925 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7860. Min Range: -5.7860
Max Act: 5.4110. Min Act: -0.1700
Data Index: 2929021 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19