Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3770 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.4031. Min Act: -0.1700
Data Index: 3813646 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.4031. Min Act: -0.1700
Data Index: 4786838 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.3875. Min Act: -0.1700
Data Index: 3813643 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.2933. Min Act: -0.1700
Data Index: 5524453 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.2776. Min Act: -0.1700
Data Index: 800785 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1361. Min Act: -0.1700
Data Index: 3866616 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1676. Min Act: -0.1700
Data Index: 771409 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1361. Min Act: -0.1700
Data Index: 545476 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1361. Min Act: -0.1700
Data Index: 923600 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1046. Min Act: -0.1700
Data Index: 7802700 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1204. Min Act: -0.1700
Data Index: 7363901 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1046. Min Act: -0.1700
Data Index: 3511586 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1046. Min Act: -0.1700
Data Index: 5663418 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1204. Min Act: -0.1700
Data Index: 4985467 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1046. Min Act: -0.1700
Data Index: 6198712 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1046. Min Act: -0.1700
Data Index: 8787445 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1046. Min Act: -0.1700
Data Index: 3286658 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.1046. Min Act: -0.1700
Data Index: 7056450 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.0731. Min Act: -0.1700
Data Index: 3717316 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4031. Min Range: -3.4031
Max Act: 3.0573. Min Act: -0.1700
Data Index: 4769267 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19