Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1715 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2082. Min Range: -6.2082
Max Act: 6.2082. Min Act: -0.1700
Data Index: 969073 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2082. Min Range: -6.2082
Max Act: 6.1770. Min Act: -0.1700
Data Index: 7281136 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2082. Min Range: -6.2082
Max Act: 6.0832. Min Act: -0.1700
Data Index: 7452859 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2082. Min Range: -6.2082
Max Act: 6.0520. Min Act: -0.1700
Data Index: 4322209 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2082. Min Range: -6.2082
Max Act: 6.0520. Min Act: -0.1700
Data Index: 5164708 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.9895. Min Act: -0.1699
Data Index: 1000298 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.9895. Min Act: -0.1700
Data Index: 4236472 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2082. Min Range: -6.2082
Max Act: 6.0207. Min Act: -0.1700
Data Index: 2248016 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.9895. Min Act: -0.1700
Data Index: 6772076 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.9582. Min Act: -0.1700
Data Index: 1552791 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.9582. Min Act: -0.1700
Data Index: 314503 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.9582. Min Act: -0.1700
Data Index: 5373578 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.9582. Min Act: -0.1700
Data Index: 7627379 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.9270. Min Act: -0.1700
Data Index: 5803454 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.8957. Min Act: -0.1700
Data Index: 3577081 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.8645. Min Act: -0.1700
Data Index: 3790686 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.8645. Min Act: -0.1700
Data Index: 2987608 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.8645. Min Act: -0.1700
Data Index: 4435245 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.8645. Min Act: -0.1700
Data Index: 2672968 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2082. Min Range: -6.2082
Max Act: 5.8645. Min Act: -0.1700
Data Index: 2630440 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19