Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 363 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0059. Min Range: -9.0059
Max Act: 9.0059. Min Act: -0.1700
Data Index: 2351499 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.8184. Min Act: -0.1700
Data Index: 1646689 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.7559. Min Act: -0.1700
Data Index: 7419463 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.6934. Min Act: -0.1700
Data Index: 8781679 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.6934. Min Act: -0.1700
Data Index: 5913766 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.6309. Min Act: -0.1700
Data Index: 6408091 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.6309. Min Act: -0.1700
Data Index: 5261729 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.6934. Min Act: -0.1700
Data Index: 298176 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.5684. Min Act: -0.1700
Data Index: 3832886 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.5684. Min Act: -0.1700
Data Index: 5956455 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.5684. Min Act: -0.1700
Data Index: 1118410 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.5684. Min Act: -0.1700
Data Index: 8088426 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.5059. Min Act: -0.1700
Data Index: 3758648 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.5059. Min Act: -0.1700
Data Index: 1488777 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.4434. Min Act: -0.1700
Data Index: 8361984 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.5059. Min Act: -0.1700
Data Index: 7927581 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.3809. Min Act: -0.1700
Data Index: 4453714 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.4434. Min Act: -0.1700
Data Index: 2958424 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.4434. Min Act: -0.1700
Data Index: 4598648 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0059. Min Range: -9.0059
Max Act: 8.4434. Min Act: -0.1700
Data Index: 5772884 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19