Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1227 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2205. Min Range: -8.2205
Max Act: 8.2205. Min Act: -0.1700
Data Index: 120609 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2205. Min Range: -8.2205
Max Act: 8.0955. Min Act: -0.1700
Data Index: 6939950 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2205. Min Range: -8.2205
Max Act: 8.0955. Min Act: -0.1700
Data Index: 5392925 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2205. Min Range: -8.2205
Max Act: 8.0330. Min Act: -0.1700
Data Index: 4537911 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.9705. Min Act: -0.1700
Data Index: 1412495 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.9080. Min Act: -0.1700
Data Index: 7902453 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.8767. Min Act: -0.1700
Data Index: 4027389 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.9080. Min Act: -0.1700
Data Index: 4779722 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.8455. Min Act: -0.1700
Data Index: 2032242 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.8142. Min Act: -0.1700
Data Index: 4651860 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.7830. Min Act: -0.1700
Data Index: 3156358 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.7830. Min Act: -0.1700
Data Index: 6805183 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.7830. Min Act: -0.1700
Data Index: 3927276 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.7517. Min Act: -0.1700
Data Index: 3654954 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.7205. Min Act: -0.1700
Data Index: 5614453 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.7205. Min Act: -0.1700
Data Index: 7098795 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.6892. Min Act: -0.1700
Data Index: 3366291 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.6892. Min Act: -0.1700
Data Index: 4064338 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.6580. Min Act: -0.1700
Data Index: 516160 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2205. Min Range: -8.2205
Max Act: 7.6892. Min Act: -0.1700
Data Index: 1503654 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19