Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0650. Min Range: -8.0650
Max Act: 8.0338. Min Act: -0.1700
Data Index: 4012546 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0650. Min Range: -8.0650
Max Act: 8.0650. Min Act: -0.1700
Data Index: 2919083 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0650. Min Range: -8.0650
Max Act: 8.0338. Min Act: -0.1700
Data Index: 4583999 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0650. Min Range: -8.0650
Max Act: 8.0025. Min Act: -0.1700
Data Index: 227017 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0650. Min Range: -8.0650
Max Act: 8.0025. Min Act: -0.1700
Data Index: 1496319 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.9713. Min Act: -0.1700
Data Index: 2976218 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0650. Min Range: -8.0650
Max Act: 8.0025. Min Act: -0.1700
Data Index: 197425 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.9713. Min Act: -0.1700
Data Index: 4661024 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.9713. Min Act: -0.1700
Data Index: 1293462 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.9713. Min Act: -0.1700
Data Index: 4842094 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.9088. Min Act: -0.1700
Data Index: 7595960 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.8775. Min Act: -0.1700
Data Index: 6829288 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.8775. Min Act: -0.1700
Data Index: 6154295 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.9400. Min Act: -0.1700
Data Index: 2261571 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.8775. Min Act: -0.1700
Data Index: 2933916 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.8775. Min Act: -0.1700
Data Index: 159167 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.8775. Min Act: -0.1700
Data Index: 1099419 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.9088. Min Act: -0.1700
Data Index: 8261133 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.8775. Min Act: -0.1700
Data Index: 7882430 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0650. Min Range: -8.0650
Max Act: 7.8775. Min Act: -0.1700
Data Index: 5337532 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19