Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 696 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.6497. Min Act: -0.1700
Data Index: 1586314 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.5247. Min Act: -0.1700
Data Index: 4173005 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.5247. Min Act: -0.1700
Data Index: 2708327 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.5247. Min Act: -0.1700
Data Index: 2356023 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.4935. Min Act: -0.1700
Data Index: 5005973 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.4622. Min Act: -0.1700
Data Index: 631224 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.4622. Min Act: -0.1700
Data Index: 8453503 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.4310. Min Act: -0.1700
Data Index: 1148257 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.3685. Min Act: -0.1700
Data Index: 4187909 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.3372. Min Act: -0.1700
Data Index: 1208581 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.3060. Min Act: -0.1700
Data Index: 4116224 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.2747. Min Act: -0.1700
Data Index: 4750692 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.3060. Min Act: -0.1700
Data Index: 6949717 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.2747. Min Act: -0.1700
Data Index: 8361790 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.2747. Min Act: -0.1700
Data Index: 1646657 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.2747. Min Act: -0.1700
Data Index: 240577 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.2747. Min Act: -0.1700
Data Index: 4883165 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.2435. Min Act: -0.1700
Data Index: 3377700 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.2122. Min Act: -0.1700
Data Index: 684834 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6497. Min Range: -5.6497
Max Act: 5.2435. Min Act: -0.1700
Data Index: 1500486 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19