Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2626 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.7271. Min Act: -0.1700
Data Index: 7908400 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.5396. Min Act: -0.1700
Data Index: 4768724 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.2896. Min Act: -0.1700
Data Index: 485988 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.2896. Min Act: -0.1700
Data Index: 3925755 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.2271. Min Act: -0.1700
Data Index: 2270107 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.1958. Min Act: -0.1700
Data Index: 4650189 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.1333. Min Act: -0.1700
Data Index: 1216576 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.1333. Min Act: -0.1700
Data Index: 1847349 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.0708. Min Act: -0.1700
Data Index: 5439159 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.0396. Min Act: -0.1700
Data Index: 3073475 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.0396. Min Act: -0.1700
Data Index: 7146757 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7271. Min Range: -8.7271
Max Act: 8.0396. Min Act: -0.1700
Data Index: 514840 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7271. Min Range: -8.7271
Max Act: 7.9771. Min Act: -0.1700
Data Index: 4385503 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7271. Min Range: -8.7271
Max Act: 7.9771. Min Act: -0.1700
Data Index: 1950515 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7271. Min Range: -8.7271
Max Act: 7.9771. Min Act: -0.1700
Data Index: 6808804 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7271. Min Range: -8.7271
Max Act: 7.9771. Min Act: -0.1700
Data Index: 7575049 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7271. Min Range: -8.7271
Max Act: 7.9458. Min Act: -0.1700
Data Index: 1142964 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7271. Min Range: -8.7271
Max Act: 7.9771. Min Act: -0.1700
Data Index: 548882 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7271. Min Range: -8.7271
Max Act: 7.9458. Min Act: -0.1700
Data Index: 385193 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7271. Min Range: -8.7271
Max Act: 7.9146. Min Act: -0.1700
Data Index: 2824822 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19