Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1764. Min Range: -9.1764
Max Act: 9.1764. Min Act: -0.1700
Data Index: 1543215 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.5514. Min Act: -0.1700
Data Index: 7664671 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.4889. Min Act: -0.1700
Data Index: 7433604 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.4889. Min Act: -0.1700
Data Index: 7907921 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.3014. Min Act: -0.1700
Data Index: 5828746 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.2389. Min Act: -0.1700
Data Index: 4708812 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.2389. Min Act: -0.1700
Data Index: 6114442 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.1764. Min Act: -0.1700
Data Index: 7458675 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.1139. Min Act: -0.1700
Data Index: 8303479 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.1139. Min Act: -0.1700
Data Index: 3924533 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.1139. Min Act: -0.1700
Data Index: 140241 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.1139. Min Act: -0.1700
Data Index: 1629456 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.0514. Min Act: -0.1700
Data Index: 4498231 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.0514. Min Act: -0.1700
Data Index: 2110201 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.0514. Min Act: -0.1700
Data Index: 3229927 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.0514. Min Act: -0.1700
Data Index: 4492238 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.0514. Min Act: -0.1700
Data Index: 5802977 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.0514. Min Act: -0.1700
Data Index: 1651850 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.0514. Min Act: -0.1700
Data Index: 818392 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1764. Min Range: -9.1764
Max Act: 8.0514. Min Act: -0.1700
Data Index: 7337189 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19