Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0021. Min Range: -7.0021
Max Act: 7.0021. Min Act: -0.1700
Data Index: 7075088 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0021. Min Range: -7.0021
Max Act: 7.0021. Min Act: -0.1700
Data Index: 410228 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.8458. Min Act: -0.1700
Data Index: 8675351 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.8146. Min Act: -0.1700
Data Index: 1564133 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.8146. Min Act: -0.1700
Data Index: 3150430 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.8146. Min Act: -0.1700
Data Index: 1976841 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.7521. Min Act: -0.1700
Data Index: 39403 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.7833. Min Act: -0.1700
Data Index: 7781544 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.7833. Min Act: -0.1700
Data Index: 7665666 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.7521. Min Act: -0.1700
Data Index: 5044290 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.7521. Min Act: -0.1700
Data Index: 3918486 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.6583. Min Act: -0.1700
Data Index: 7290393 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.6583. Min Act: -0.1700
Data Index: 4143087 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.6583. Min Act: -0.1700
Data Index: 6371487 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.6271. Min Act: -0.1700
Data Index: 1633580 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.6271. Min Act: -0.1700
Data Index: 7361442 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.6271. Min Act: -0.1700
Data Index: 6430787 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.6271. Min Act: -0.1700
Data Index: 207077 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.6271. Min Act: -0.1700
Data Index: 646414 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0021. Min Range: -7.0021
Max Act: 6.5958. Min Act: -0.1700
Data Index: 452850 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19