Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.9874. Min Act: -0.1700
Data Index: 3872908 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.7999. Min Act: -0.1700
Data Index: 4633746 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.7999. Min Act: -0.1700
Data Index: 2357692 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.7374. Min Act: -0.1700
Data Index: 3719336 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.7374. Min Act: -0.1700
Data Index: 1069168 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.6749. Min Act: -0.1700
Data Index: 4905565 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.6749. Min Act: -0.1700
Data Index: 5659663 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.6749. Min Act: -0.1700
Data Index: 4583948 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.6436. Min Act: -0.1700
Data Index: 7625253 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.6124. Min Act: -0.1700
Data Index: 2339758 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.6124. Min Act: -0.1700
Data Index: 7867063 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.5811. Min Act: -0.1700
Data Index: 6716854 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.5499. Min Act: -0.1700
Data Index: 1715792 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.5499. Min Act: -0.1700
Data Index: 3026140 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.5186. Min Act: -0.1700
Data Index: 6811591 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.5186. Min Act: -0.1700
Data Index: 6511315 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.5186. Min Act: -0.1700
Data Index: 1867866 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.5186. Min Act: -0.1700
Data Index: 3852883 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.5186. Min Act: -0.1700
Data Index: 976826 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9874. Min Range: -5.9874
Max Act: 5.5186. Min Act: -0.1700
Data Index: 1046830 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19