Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1075 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6726. Min Range: -9.6726
Max Act: 9.6726. Min Act: -0.1700
Data Index: 6862834 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6726. Min Range: -9.6726
Max Act: 9.3601. Min Act: -0.1700
Data Index: 4551621 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6726. Min Range: -9.6726
Max Act: 9.1726. Min Act: -0.1700
Data Index: 4134606 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6726. Min Range: -9.6726
Max Act: 9.1726. Min Act: -0.1700
Data Index: 2624279 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6726. Min Range: -9.6726
Max Act: 9.0476. Min Act: -0.1700
Data Index: 1228359 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6726. Min Range: -9.6726
Max Act: 9.1101. Min Act: -0.1700
Data Index: 6941398 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6726. Min Range: -9.6726
Max Act: 9.0476. Min Act: -0.1700
Data Index: 5869632 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9851. Min Act: -0.1700
Data Index: 3651035 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9851. Min Act: -0.1700
Data Index: 5050269 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9851. Min Act: -0.1700
Data Index: 3966671 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9851. Min Act: -0.1700
Data Index: 4556398 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9851. Min Act: -0.1700
Data Index: 3218929 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.8601. Min Act: -0.1700
Data Index: 705278 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9226. Min Act: -0.1700
Data Index: 7153680 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9226. Min Act: -0.1700
Data Index: 5618247 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9226. Min Act: -0.1700
Data Index: 1144837 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.8601. Min Act: -0.1700
Data Index: 5598668 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9226. Min Act: -0.1700
Data Index: 1942992 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9226. Min Act: -0.1700
Data Index: 1696286 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6726. Min Range: -9.6726
Max Act: 8.9226. Min Act: -0.1700
Data Index: 2943658 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19