Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6369 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.7324. Min Act: -0.1700
Data Index: 2860184 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.7012. Min Act: -0.1700
Data Index: 1322327 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.7012. Min Act: -0.1700
Data Index: 47292 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.6387. Min Act: -0.1700
Data Index: 5379489 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.6074. Min Act: -0.1700
Data Index: 3688572 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.5449. Min Act: -0.1700
Data Index: 7321586 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.4824. Min Act: -0.1700
Data Index: 7332232 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.5137. Min Act: -0.1700
Data Index: 6794281 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.4199. Min Act: -0.1700
Data Index: 6019533 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.4199. Min Act: -0.1700
Data Index: 5552652 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.4199. Min Act: -0.1700
Data Index: 8098797 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.4199. Min Act: -0.1700
Data Index: 606856 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.3887. Min Act: -0.1700
Data Index: 3259788 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.3887. Min Act: -0.1700
Data Index: 4273766 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.3887. Min Act: -0.1700
Data Index: 5257177 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.3574. Min Act: -0.1700
Data Index: 2706249 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.3574. Min Act: -0.1700
Data Index: 7031609 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.3887. Min Act: -0.1700
Data Index: 7963655 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.3262. Min Act: -0.1700
Data Index: 5471748 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7324. Min Range: -6.7324
Max Act: 6.3262. Min Act: -0.1700
Data Index: 3282674 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19