Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1227 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3052. Min Range: -6.3052
Max Act: 6.3052. Min Act: -0.1700
Data Index: 5917747 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3052. Min Range: -6.3052
Max Act: 6.0552. Min Act: -0.1700
Data Index: 8303759 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3052. Min Range: -6.3052
Max Act: 6.0865. Min Act: -0.1700
Data Index: 4084510 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.9615. Min Act: -0.1700
Data Index: 323180 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.9302. Min Act: -0.1700
Data Index: 5026064 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.9302. Min Act: -0.1700
Data Index: 3235018 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.8990. Min Act: -0.1700
Data Index: 8281341 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.9302. Min Act: -0.1700
Data Index: 4204168 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.8990. Min Act: -0.1700
Data Index: 3918514 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.8990. Min Act: -0.1700
Data Index: 6068224 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.8365. Min Act: -0.1700
Data Index: 6537269 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.8365. Min Act: -0.1700
Data Index: 2239322 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.7740. Min Act: -0.1700
Data Index: 1510996 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.7427. Min Act: -0.1700
Data Index: 526087 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.7427. Min Act: -0.1700
Data Index: 4194569 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.7115. Min Act: -0.1700
Data Index: 1449245 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.6490. Min Act: -0.1700
Data Index: 1547033 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.6490. Min Act: -0.1700
Data Index: 8206704 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.6490. Min Act: -0.1700
Data Index: 4276535 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3052. Min Range: -6.3052
Max Act: 5.6177. Min Act: -0.1700
Data Index: 6298628 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19