Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3647 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3101. Min Range: -4.3101
Max Act: 4.3101. Min Act: -0.1700
Data Index: 6548644 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3101. Min Range: -4.3101
Max Act: 4.2475. Min Act: -0.1700
Data Index: 1082011 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3101. Min Range: -4.3101
Max Act: 4.1850. Min Act: -0.1700
Data Index: 3024366 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3101. Min Range: -4.3101
Max Act: 4.0913. Min Act: -0.1700
Data Index: 1784315 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3101. Min Range: -4.3101
Max Act: 4.1225. Min Act: -0.1700
Data Index: 5041422 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3101. Min Range: -4.3101
Max Act: 4.0913. Min Act: -0.1700
Data Index: 5676385 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3101. Min Range: -4.3101
Max Act: 4.0913. Min Act: -0.1700
Data Index: 3846007 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3101. Min Range: -4.3101
Max Act: 4.0288. Min Act: -0.1700
Data Index: 4586030 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3101. Min Range: -4.3101
Max Act: 4.0288. Min Act: -0.1700
Data Index: 4723904 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3101. Min Range: -4.3101
Max Act: 4.0288. Min Act: -0.1700
Data Index: 1487963 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3101. Min Range: -4.3101
Max Act: 3.9975. Min Act: -0.1700
Data Index: 7571866 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3101. Min Range: -4.3101
Max Act: 3.9975. Min Act: -0.1700
Data Index: 8565193 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3101. Min Range: -4.3101
Max Act: 3.9975. Min Act: -0.1700
Data Index: 846016 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3101. Min Range: -4.3101
Max Act: 3.9662. Min Act: -0.1700
Data Index: 5513752 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3101. Min Range: -4.3101
Max Act: 3.9975. Min Act: -0.1700
Data Index: 3573927 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3101. Min Range: -4.3101
Max Act: 3.9662. Min Act: -0.1700
Data Index: 1322386 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3101. Min Range: -4.3101
Max Act: 3.9350. Min Act: -0.1700
Data Index: 3949135 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3101. Min Range: -4.3101
Max Act: 3.9037. Min Act: -0.1700
Data Index: 8228984 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3101. Min Range: -4.3101
Max Act: 3.9350. Min Act: -0.1700
Data Index: 6582593 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3101. Min Range: -4.3101
Max Act: 3.9350. Min Act: -0.1700
Data Index: 2862909 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19