Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5834 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1218. Min Range: -5.1218
Max Act: 5.1218. Min Act: -0.1700
Data Index: 155649 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1218. Min Range: -5.1218
Max Act: 5.1218. Min Act: -0.1700
Data Index: 3507106 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1218. Min Range: -5.1218
Max Act: 5.0593. Min Act: -0.1700
Data Index: 3013544 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1218. Min Range: -5.1218
Max Act: 5.0280. Min Act: -0.1700
Data Index: 6720304 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.9967. Min Act: -0.1700
Data Index: 1603317 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.9342. Min Act: -0.1700
Data Index: 8199367 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.9342. Min Act: -0.1700
Data Index: 2911037 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.9030. Min Act: -0.1700
Data Index: 1515080 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.9030. Min Act: -0.1700
Data Index: 8487422 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.9030. Min Act: -0.1700
Data Index: 6855347 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.9030. Min Act: -0.1700
Data Index: 118790 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.9030. Min Act: -0.1700
Data Index: 4032839 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.9030. Min Act: -0.1700
Data Index: 5149394 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.8717. Min Act: -0.1700
Data Index: 1942771 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.8717. Min Act: -0.1700
Data Index: 3571678 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.8092. Min Act: -0.1700
Data Index: 7336672 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.8405. Min Act: -0.1700
Data Index: 4678364 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.8717. Min Act: -0.1700
Data Index: 7927758 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.8405. Min Act: -0.1700
Data Index: 4564349 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1218. Min Range: -5.1218
Max Act: 4.8405. Min Act: -0.1700
Data Index: 6095883 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19