Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.9859. Min Act: -0.1700
Data Index: 7200599 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.6422. Min Act: -0.1700
Data Index: 6784474 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.5484. Min Act: -0.1700
Data Index: 720378 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.5484. Min Act: -0.1700
Data Index: 5982673 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.5172. Min Act: -0.1700
Data Index: 5729634 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.5172. Min Act: -0.1700
Data Index: 8076027 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.5172. Min Act: -0.1700
Data Index: 5885033 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.4859. Min Act: -0.1700
Data Index: 293985 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.4859. Min Act: -0.1700
Data Index: 8435542 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.4547. Min Act: -0.1700
Data Index: 3871472 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.4547. Min Act: -0.1700
Data Index: 5839948 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.4547. Min Act: -0.1700
Data Index: 8301437 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.4234. Min Act: -0.1700
Data Index: 4675120 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.4234. Min Act: -0.1700
Data Index: 3481608 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.4547. Min Act: -0.1700
Data Index: 7340896 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.4234. Min Act: -0.1700
Data Index: 1759773 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.3609. Min Act: -0.1700
Data Index: 3275061 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.3922. Min Act: -0.1700
Data Index: 6482588 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.3922. Min Act: -0.1700
Data Index: 818647 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9859. Min Range: -4.9859
Max Act: 4.3922. Min Act: -0.1700
Data Index: 6890872 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19