Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4812 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.9422. Min Act: -0.1700
Data Index: 5298168 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.9110. Min Act: -0.1700
Data Index: 6968223 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.8797. Min Act: -0.1700
Data Index: 8674377 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.5360. Min Act: -0.1700
Data Index: 4974886 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.4422. Min Act: -0.1700
Data Index: 7860810 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.4422. Min Act: -0.1700
Data Index: 506749 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.4110. Min Act: -0.1700
Data Index: 4701978 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.4422. Min Act: -0.1700
Data Index: 4801394 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.3797. Min Act: -0.1700
Data Index: 668760 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.3485. Min Act: -0.1700
Data Index: 2700339 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.3485. Min Act: -0.1700
Data Index: 332923 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.3172. Min Act: -0.1700
Data Index: 789375 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.2860. Min Act: -0.1700
Data Index: 6927737 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.2860. Min Act: -0.1700
Data Index: 6029254 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.2860. Min Act: -0.1700
Data Index: 2967798 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.2860. Min Act: -0.1700
Data Index: 6491578 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.2547. Min Act: -0.1700
Data Index: 7933726 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.2547. Min Act: -0.1700
Data Index: 1844035 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.2547. Min Act: -0.1700
Data Index: 4087241 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9422. Min Range: -4.9422
Max Act: 4.2547. Min Act: -0.1700
Data Index: 7197892 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19