Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4868 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.9388. Min Act: -0.1700
Data Index: 3006303 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.8138. Min Act: -0.1700
Data Index: 8003357 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.6263. Min Act: -0.1700
Data Index: 3673983 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.3763. Min Act: -0.1700
Data Index: 65933 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.3763. Min Act: -0.1700
Data Index: 2071830 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.3138. Min Act: -0.1700
Data Index: 2702177 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.3138. Min Act: -0.1700
Data Index: 7824767 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.2513. Min Act: -0.1700
Data Index: 3079594 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.2513. Min Act: -0.1700
Data Index: 6704029 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.1888. Min Act: -0.1700
Data Index: 1403479 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.1263. Min Act: -0.1700
Data Index: 3401432 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.1263. Min Act: -0.1700
Data Index: 3304999 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.1263. Min Act: -0.1700
Data Index: 3299182 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.0638. Min Act: -0.1700
Data Index: 1355573 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.1263. Min Act: -0.1700
Data Index: 1326794 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.0638. Min Act: -0.1700
Data Index: 6445885 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.0638. Min Act: -0.1700
Data Index: 6394583 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.0013. Min Act: -0.1700
Data Index: 5839874 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.0013. Min Act: -0.1700
Data Index: 5377805 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9388. Min Range: -8.9388
Max Act: 8.0013. Min Act: -0.1700
Data Index: 6002538 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19