Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2397 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.7748. Min Act: -0.1700
Data Index: 8622249 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.7436. Min Act: -0.1700
Data Index: 1344399 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.7436. Min Act: -0.1700
Data Index: 6934283 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.7123. Min Act: -0.1700
Data Index: 2637423 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.6811. Min Act: -0.1700
Data Index: 6891741 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.6811. Min Act: -0.1700
Data Index: 6572374 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.7123. Min Act: -0.1700
Data Index: 2544741 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.6498. Min Act: -0.1700
Data Index: 8389102 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.6498. Min Act: -0.1700
Data Index: 1653241 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.6498. Min Act: -0.1700
Data Index: 7430142 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.6186. Min Act: -0.1700
Data Index: 779972 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.6186. Min Act: -0.1700
Data Index: 5510257 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.6498. Min Act: -0.1700
Data Index: 3030215 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.5873. Min Act: -0.1700
Data Index: 3636042 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.5873. Min Act: -0.1700
Data Index: 3123177 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.5873. Min Act: -0.1700
Data Index: 8016092 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.5561. Min Act: -0.1700
Data Index: 3190475 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.5561. Min Act: -0.1700
Data Index: 8036704 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.5561. Min Act: -0.1700
Data Index: 238021 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7748. Min Range: -5.7748
Max Act: 5.5561. Min Act: -0.1700
Data Index: 606223 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19