Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.3731. Min Act: -0.1700
Data Index: 5558940 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.3106. Min Act: -0.1700
Data Index: 1964371 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.3106. Min Act: -0.1700
Data Index: 8150694 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.3419. Min Act: -0.1700
Data Index: 6328232 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.2481. Min Act: -0.1700
Data Index: 4842760 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.2169. Min Act: -0.1700
Data Index: 7113942 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.1856. Min Act: -0.1700
Data Index: 5005751 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.1856. Min Act: -0.1700
Data Index: 2640881 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.1544. Min Act: -0.1700
Data Index: 7007961 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.1544. Min Act: -0.1700
Data Index: 321607 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.1544. Min Act: -0.1700
Data Index: 697381 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.1544. Min Act: -0.1700
Data Index: 6774229 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.1544. Min Act: -0.1700
Data Index: 3369710 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.1231. Min Act: -0.1700
Data Index: 1320197 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.0919. Min Act: -0.1700
Data Index: 6462601 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.0919. Min Act: -0.1700
Data Index: 8150695 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.0919. Min Act: -0.1700
Data Index: 3407681 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.0919. Min Act: -0.1700
Data Index: 4550039 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.0919. Min Act: -0.1700
Data Index: 6297392 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3731. Min Range: -5.3731
Max Act: 5.0919. Min Act: -0.1700
Data Index: 2210390 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19