Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3263. Min Range: -8.3263
Max Act: 8.3263. Min Act: -0.1700
Data Index: 4525394 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3263. Min Range: -8.3263
Max Act: 8.1701. Min Act: -0.1700
Data Index: 3061488 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3263. Min Range: -8.3263
Max Act: 8.0451. Min Act: -0.1700
Data Index: 2063351 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.8888. Min Act: -0.1700
Data Index: 5286763 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.8576. Min Act: -0.1700
Data Index: 5204612 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.8263. Min Act: -0.1700
Data Index: 8796676 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.6388. Min Act: -0.1700
Data Index: 1993401 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.6076. Min Act: -0.1700
Data Index: 7628843 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.5451. Min Act: -0.1700
Data Index: 7016707 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.5138. Min Act: -0.1700
Data Index: 7709612 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.5138. Min Act: -0.1700
Data Index: 4042286 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.5138. Min Act: -0.1700
Data Index: 4366789 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.5138. Min Act: -0.1700
Data Index: 689722 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.4513. Min Act: -0.1700
Data Index: 2063151 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.5138. Min Act: -0.1700
Data Index: 944938 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.4826. Min Act: -0.1700
Data Index: 8276336 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.5138. Min Act: -0.1700
Data Index: 3004381 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.4826. Min Act: -0.1700
Data Index: 8564176 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.5138. Min Act: -0.1700
Data Index: 189165 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3263. Min Range: -8.3263
Max Act: 7.4826. Min Act: -0.1700
Data Index: 6146519 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19