Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5277 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.5969. Min Act: -0.1700
Data Index: 4564923 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.3782. Min Act: -0.1700
Data Index: 5909546 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.3782. Min Act: -0.1700
Data Index: 769480 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.3782. Min Act: -0.1700
Data Index: 3741287 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.2219. Min Act: -0.1700
Data Index: 3270618 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.2219. Min Act: -0.1700
Data Index: 3001400 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.2219. Min Act: -0.1700
Data Index: 5051277 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.1907. Min Act: -0.1700
Data Index: 4042551 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.1907. Min Act: -0.1700
Data Index: 2125652 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.1594. Min Act: -0.1700
Data Index: 2118363 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.1594. Min Act: -0.1700
Data Index: 5104037 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.1282. Min Act: -0.1700
Data Index: 1046405 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.1282. Min Act: -0.1700
Data Index: 8370853 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.1282. Min Act: -0.1700
Data Index: 2333613 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.0969. Min Act: -0.1700
Data Index: 8525353 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.0344. Min Act: -0.1700
Data Index: 5104038 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.0657. Min Act: -0.1700
Data Index: 1544720 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.0657. Min Act: -0.1700
Data Index: 6551258 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.0969. Min Act: -0.1700
Data Index: 6048306 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5969. Min Range: -5.5969
Max Act: 5.0657. Min Act: -0.1700
Data Index: 4378362 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19