Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6378 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.6747. Min Act: -0.1700
Data Index: 7763882 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.6435. Min Act: -0.1700
Data Index: 3009436 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.6122. Min Act: -0.1700
Data Index: 7933404 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.5497. Min Act: -0.1700
Data Index: 5872228 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.5497. Min Act: -0.1700
Data Index: 4726559 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4872. Min Act: -0.1700
Data Index: 3573577 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4872. Min Act: -0.1700
Data Index: 1221490 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4560. Min Act: -0.1700
Data Index: 1627647 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4560. Min Act: -0.1700
Data Index: 4119488 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4560. Min Act: -0.1700
Data Index: 5342703 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4560. Min Act: -0.1700
Data Index: 5095924 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4560. Min Act: -0.1700
Data Index: 1168156 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4560. Min Act: -0.1700
Data Index: 8702886 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4247. Min Act: -0.1700
Data Index: 4304590 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4247. Min Act: -0.1700
Data Index: 105095 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4247. Min Act: -0.1700
Data Index: 2298804 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4560. Min Act: -0.1700
Data Index: 946867 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4247. Min Act: -0.1700
Data Index: 7533303 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4247. Min Act: -0.1700
Data Index: 8580496 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6747. Min Range: -4.6747
Max Act: 4.4247. Min Act: -0.1700
Data Index: 4006104 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19