Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1199 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5946. Min Range: -12.5946
Max Act: 12.5946. Min Act: -0.1700
Data Index: 526519 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5946. Min Range: -12.5946
Max Act: 12.5946. Min Act: -0.1700
Data Index: 127541 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5946. Min Range: -12.5946
Max Act: 12.4696. Min Act: -0.1700
Data Index: 2593200 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5946. Min Range: -12.5946
Max Act: 12.2196. Min Act: -0.1700
Data Index: 8748861 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5946. Min Range: -12.5946
Max Act: 12.0946. Min Act: -0.1700
Data Index: 1325358 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5946. Min Range: -12.5946
Max Act: 12.0946. Min Act: -0.1700
Data Index: 7497928 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5946. Min Range: -12.5946
Max Act: 12.0946. Min Act: -0.1700
Data Index: 542786 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.9696. Min Act: -0.1700
Data Index: 6054724 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5946. Min Range: -12.5946
Max Act: 12.0321. Min Act: -0.1700
Data Index: 4993783 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.9071. Min Act: -0.1700
Data Index: 4193807 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.9071. Min Act: -0.1700
Data Index: 6111553 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.8446. Min Act: -0.1700
Data Index: 3728823 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.8446. Min Act: -0.1700
Data Index: 8597011 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.8446. Min Act: -0.1700
Data Index: 6959137 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.8446. Min Act: -0.1700
Data Index: 5217828 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.7821. Min Act: -0.1700
Data Index: 368053 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.7821. Min Act: -0.1700
Data Index: 3719730 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.7821. Min Act: -0.1700
Data Index: 1792088 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.7196. Min Act: -0.1700
Data Index: 4927352 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5946. Min Range: -12.5946
Max Act: 11.6571. Min Act: -0.1700
Data Index: 846588 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19