Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4864 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0375. Min Range: -12.0375
Max Act: 12.0375. Min Act: -0.1700
Data Index: 6454512 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.9750. Min Act: -0.1700
Data Index: 555333 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.5375. Min Act: -0.1700
Data Index: 8458795 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.4125. Min Act: -0.1700
Data Index: 8089148 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.4125. Min Act: -0.1700
Data Index: 2652569 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.4125. Min Act: -0.1700
Data Index: 8136330 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.2875. Min Act: -0.1700
Data Index: 5562292 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.2250. Min Act: -0.1700
Data Index: 5029400 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.2250. Min Act: -0.1700
Data Index: 6035094 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.1625. Min Act: -0.1700
Data Index: 8677518 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.1000. Min Act: -0.1700
Data Index: 6254153 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.1625. Min Act: -0.1700
Data Index: 4650668 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.1000. Min Act: -0.1700
Data Index: 2497438 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.0375. Min Act: -0.1700
Data Index: 8766359 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.0375. Min Act: -0.1700
Data Index: 6822242 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0375. Min Range: -12.0375
Max Act: 11.0375. Min Act: -0.1700
Data Index: 1802203 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0375. Min Range: -12.0375
Max Act: 10.9125. Min Act: -0.1700
Data Index: 5118071 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0375. Min Range: -12.0375
Max Act: 10.9125. Min Act: -0.1700
Data Index: 4153006 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0375. Min Range: -12.0375
Max Act: 10.8500. Min Act: -0.1700
Data Index: 7778457 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0375. Min Range: -12.0375
Max Act: 10.8500. Min Act: -0.1700
Data Index: 1607031 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19