Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5009 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2576. Min Range: -9.2576
Max Act: 9.2576. Min Act: -0.1700
Data Index: 4679355 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2576. Min Range: -9.2576
Max Act: 9.0701. Min Act: -0.1700
Data Index: 3810089 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2576. Min Range: -9.2576
Max Act: 9.0701. Min Act: -0.1700
Data Index: 5395856 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2576. Min Range: -9.2576
Max Act: 9.0076. Min Act: -0.1700
Data Index: 5395854 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.9451. Min Act: -0.1700
Data Index: 2268429 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.9451. Min Act: -0.1700
Data Index: 631395 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.8826. Min Act: -0.1700
Data Index: 6137952 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.7576. Min Act: -0.1700
Data Index: 2818775 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.7576. Min Act: -0.1700
Data Index: 7839928 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.7576. Min Act: -0.1700
Data Index: 2437485 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.7576. Min Act: -0.1700
Data Index: 4728623 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.7576. Min Act: -0.1700
Data Index: 3982923 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.7576. Min Act: -0.1700
Data Index: 2284598 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.6951. Min Act: -0.1700
Data Index: 4464482 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.6326. Min Act: -0.1700
Data Index: 8806539 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.5076. Min Act: -0.1700
Data Index: 3808294 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.5076. Min Act: -0.1700
Data Index: 6802745 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.5076. Min Act: -0.1700
Data Index: 862407 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.5076. Min Act: -0.1700
Data Index: 4260211 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2576. Min Range: -9.2576
Max Act: 8.5076. Min Act: -0.1700
Data Index: 563629 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19