Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2057 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3784. Min Range: -9.3784
Max Act: 9.3784. Min Act: -0.1700
Data Index: 3356788 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3784. Min Range: -9.3784
Max Act: 9.0034. Min Act: -0.1700
Data Index: 227717 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.9409. Min Act: -0.1700
Data Index: 227714 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.8159. Min Act: -0.1700
Data Index: 4658605 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.6909. Min Act: -0.1700
Data Index: 2732344 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.7534. Min Act: -0.1700
Data Index: 1820853 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.6909. Min Act: -0.1700
Data Index: 7477042 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.5659. Min Act: -0.1700
Data Index: 2251636 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.5659. Min Act: -0.1700
Data Index: 8299511 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.5034. Min Act: -0.1700
Data Index: 227713 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.5034. Min Act: -0.1700
Data Index: 227716 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.5034. Min Act: -0.1700
Data Index: 8686866 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.5034. Min Act: -0.1700
Data Index: 2247543 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.5034. Min Act: -0.1700
Data Index: 4575223 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.4409. Min Act: -0.1700
Data Index: 5404238 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.4409. Min Act: -0.1700
Data Index: 1965403 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.4409. Min Act: -0.1700
Data Index: 227720 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.3784. Min Act: -0.1700
Data Index: 5184478 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.3784. Min Act: -0.1700
Data Index: 5138474 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3784. Min Range: -9.3784
Max Act: 8.3784. Min Act: -0.1700
Data Index: 8787387 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19