Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2033 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.8688. Min Act: -0.1700
Data Index: 3034181 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.8063. Min Act: -0.1700
Data Index: 3061090 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.6813. Min Act: -0.1700
Data Index: 3023347 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.6813. Min Act: -0.1700
Data Index: 8197357 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.5876. Min Act: -0.1700
Data Index: 2352244 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.5876. Min Act: -0.1700
Data Index: 7373580 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.5876. Min Act: -0.1700
Data Index: 7778627 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.5563. Min Act: -0.1700
Data Index: 1640836 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.5563. Min Act: -0.1700
Data Index: 6480679 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.5251. Min Act: -0.1700
Data Index: 3828101 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.4938. Min Act: -0.1700
Data Index: 5597784 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.5251. Min Act: -0.1700
Data Index: 739140 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.4938. Min Act: -0.1700
Data Index: 8188359 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.4938. Min Act: -0.1700
Data Index: 4440372 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.4626. Min Act: -0.1700
Data Index: 6573262 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.4313. Min Act: -0.1700
Data Index: 7373579 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.4313. Min Act: -0.1700
Data Index: 6247883 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.4313. Min Act: -0.1700
Data Index: 8009043 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.4001. Min Act: -0.1700
Data Index: 960914 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8688. Min Range: -5.8688
Max Act: 5.4001. Min Act: -0.1700
Data Index: 3577870 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19