Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0059. Min Range: -8.0059
Max Act: 8.0059. Min Act: -0.1700
Data Index: 7887644 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.7559. Min Act: -0.1700
Data Index: 3500474 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.7559. Min Act: -0.1700
Data Index: 7590207 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.7559. Min Act: -0.1700
Data Index: 6071604 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.6934. Min Act: -0.1700
Data Index: 3156112 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.6934. Min Act: -0.1700
Data Index: 8673756 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.5684. Min Act: -0.1700
Data Index: 2490903 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.5684. Min Act: -0.1700
Data Index: 3687804 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.5059. Min Act: -0.1700
Data Index: 1269748 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.5372. Min Act: -0.1700
Data Index: 3723263 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.4747. Min Act: -0.1700
Data Index: 6428616 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.4747. Min Act: -0.1700
Data Index: 8790364 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.4434. Min Act: -0.1700
Data Index: 6427076 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.4747. Min Act: -0.1700
Data Index: 5702023 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.4747. Min Act: -0.1700
Data Index: 1281502 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.4434. Min Act: -0.1700
Data Index: 5133301 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.4122. Min Act: -0.1700
Data Index: 5637454 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.3809. Min Act: -0.1700
Data Index: 6090159 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.3809. Min Act: -0.1700
Data Index: 1810894 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0059. Min Range: -8.0059
Max Act: 7.3497. Min Act: -0.1700
Data Index: 3145994 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19