Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5099 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.3593. Min Act: -0.1700
Data Index: 7288852 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.2655. Min Act: -0.1700
Data Index: 8209041 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.2343. Min Act: -0.1700
Data Index: 4840502 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.2343. Min Act: -0.1700
Data Index: 76666 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.2030. Min Act: -0.1700
Data Index: 3489007 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.2030. Min Act: -0.1700
Data Index: 6050014 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.1718. Min Act: -0.1700
Data Index: 5092030 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.1405. Min Act: -0.1700
Data Index: 4185844 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.1718. Min Act: -0.1700
Data Index: 3516584 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.1718. Min Act: -0.1700
Data Index: 6587765 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.1405. Min Act: -0.1700
Data Index: 6454375 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.1405. Min Act: -0.1700
Data Index: 3165585 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.1405. Min Act: -0.1700
Data Index: 4955210 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.0780. Min Act: -0.1700
Data Index: 8154881 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.1093. Min Act: -0.1700
Data Index: 1460121 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.1093. Min Act: -0.1700
Data Index: 7522627 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.0780. Min Act: -0.1700
Data Index: 4799772 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.0468. Min Act: -0.1700
Data Index: 2881821 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.0780. Min Act: -0.1700
Data Index: 5382328 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3593. Min Range: -5.3593
Max Act: 5.0780. Min Act: -0.1700
Data Index: 3940565 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19