Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3890 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4210. Min Range: -7.4210
Max Act: 7.4210. Min Act: -0.1700
Data Index: 2708336 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4210. Min Range: -7.4210
Max Act: 7.3273. Min Act: -0.1700
Data Index: 1573080 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4210. Min Range: -7.4210
Max Act: 7.0460. Min Act: -0.1700
Data Index: 7931191 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.9210. Min Act: -0.1700
Data Index: 2838696 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.9523. Min Act: -0.1700
Data Index: 6747364 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.9523. Min Act: -0.1700
Data Index: 3935346 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.9523. Min Act: -0.1700
Data Index: 4568260 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.9210. Min Act: -0.1700
Data Index: 4618604 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.8898. Min Act: -0.1700
Data Index: 591978 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.8585. Min Act: -0.1700
Data Index: 5796987 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.8273. Min Act: -0.1700
Data Index: 2995549 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.8273. Min Act: -0.1700
Data Index: 8413781 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.8273. Min Act: -0.1700
Data Index: 161422 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.7960. Min Act: -0.1700
Data Index: 5281702 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.7648. Min Act: -0.1700
Data Index: 4183999 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.6710. Min Act: -0.1700
Data Index: 7650433 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.6398. Min Act: -0.1700
Data Index: 3717635 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.6398. Min Act: -0.1700
Data Index: 5807335 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.6710. Min Act: -0.1700
Data Index: 5424166 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.6398. Min Act: -0.1700
Data Index: 5407254 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19