Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5062 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2405. Min Range: -7.2405
Max Act: 7.2405. Min Act: -0.1700
Data Index: 3046792 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2405. Min Range: -7.2405
Max Act: 7.2093. Min Act: -0.1700
Data Index: 4177442 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.8343. Min Act: -0.1700
Data Index: 6798605 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.7093. Min Act: -0.1700
Data Index: 1655173 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.7093. Min Act: -0.1700
Data Index: 5463555 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.6780. Min Act: -0.1700
Data Index: 4124155 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.6468. Min Act: -0.1700
Data Index: 4851998 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.6468. Min Act: -0.1700
Data Index: 5198658 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5843. Min Act: -0.1700
Data Index: 4124396 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.6155. Min Act: -0.1700
Data Index: 2725111 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5843. Min Act: -0.1700
Data Index: 458548 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5530. Min Act: -0.1700
Data Index: 8202708 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5843. Min Act: -0.1700
Data Index: 265182 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5218. Min Act: -0.1700
Data Index: 5361127 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5218. Min Act: -0.1700
Data Index: 491389 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5843. Min Act: -0.1700
Data Index: 843773 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5530. Min Act: -0.1700
Data Index: 989778 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5530. Min Act: -0.1700
Data Index: 7087375 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5218. Min Act: -0.1700
Data Index: 5487484 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2405. Min Range: -7.2405
Max Act: 6.5218. Min Act: -0.1700
Data Index: 4508355 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19