Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2731. Min Range: -8.2731
Max Act: 8.2731. Min Act: -0.1700
Data Index: 6583098 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2731. Min Range: -8.2731
Max Act: 8.0856. Min Act: -0.1700
Data Index: 7550638 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2731. Min Range: -8.2731
Max Act: 8.0231. Min Act: -0.1700
Data Index: 760203 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2731. Min Range: -8.2731
Max Act: 8.0856. Min Act: -0.1700
Data Index: 442500 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2731. Min Range: -8.2731
Max Act: 8.0856. Min Act: -0.1700
Data Index: 7478325 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.9606. Min Act: -0.1700
Data Index: 6017639 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.8981. Min Act: -0.1700
Data Index: 3261211 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.8981. Min Act: -0.1700
Data Index: 4675783 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.8981. Min Act: -0.1700
Data Index: 3219931 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.8356. Min Act: -0.1700
Data Index: 8645921 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.7731. Min Act: -0.1700
Data Index: 7024135 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.7731. Min Act: -0.1700
Data Index: 1855242 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.7731. Min Act: -0.1700
Data Index: 2894762 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.7731. Min Act: -0.1700
Data Index: 326722 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.7731. Min Act: -0.1700
Data Index: 3417455 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.7106. Min Act: -0.1700
Data Index: 4397404 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.7106. Min Act: -0.1700
Data Index: 6313084 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.7106. Min Act: -0.1700
Data Index: 4531262 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.7106. Min Act: -0.1700
Data Index: 4115919 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2731. Min Range: -8.2731
Max Act: 7.7106. Min Act: -0.1700
Data Index: 1550733 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19