Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4991 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.5062. Min Act: -0.1700
Data Index: 5684534 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.4750. Min Act: -0.1700
Data Index: 5274888 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.4437. Min Act: -0.1700
Data Index: 1659677 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.4125. Min Act: -0.1700
Data Index: 2862834 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.4125. Min Act: -0.1700
Data Index: 5372157 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.3500. Min Act: -0.1700
Data Index: 6167850 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.3500. Min Act: -0.1700
Data Index: 2862835 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.3500. Min Act: -0.1700
Data Index: 565165 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2875. Min Act: -0.1700
Data Index: 7982056 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2875. Min Act: -0.1700
Data Index: 8201807 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2562. Min Act: -0.1700
Data Index: 3367970 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2562. Min Act: -0.1700
Data Index: 5903297 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2562. Min Act: -0.1700
Data Index: 4300722 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2250. Min Act: -0.1700
Data Index: 2837145 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2250. Min Act: -0.1700
Data Index: 5179712 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2250. Min Act: -0.1700
Data Index: 1608924 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2250. Min Act: -0.1700
Data Index: 450142 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2250. Min Act: -0.1700
Data Index: 1348335 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2250. Min Act: -0.1700
Data Index: 1183076 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5062. Min Range: -5.5062
Max Act: 5.2562. Min Act: -0.1700
Data Index: 1971648 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19