Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.7344. Min Act: -0.1700
Data Index: 4702248 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5156. Min Range: -7.5156
Max Act: 7.1719. Min Act: -0.1700
Data Index: 5137067 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5156. Min Range: -7.5156
Max Act: 7.0469. Min Act: -0.1700
Data Index: 1426628 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5156. Min Range: -7.5156
Max Act: 7.0156. Min Act: -0.1700
Data Index: 4960565 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5156. Min Range: -7.5156
Max Act: 5.6094. Min Act: -0.1700
Data Index: 2033188 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5156. Min Range: -7.5156
Max Act: 7.3594. Min Act: -0.1700
Data Index: 5829313 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.7969. Min Act: -0.1700
Data Index: 7408602 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.9531. Min Act: -0.1700
Data Index: 6411298 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5156. Min Range: -7.5156
Max Act: 5.9219. Min Act: -0.1700
Data Index: 5488143 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.0156. Min Act: -0.1700
Data Index: 4926041 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.7656. Min Act: -0.1700
Data Index: 6569192 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.9219. Min Act: -0.1700
Data Index: 6928571 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.6406. Min Act: -0.1700
Data Index: 1407495 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.8281. Min Act: -0.1700
Data Index: 3348464 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.8281. Min Act: -0.1699
Data Index: 4569803 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.8281. Min Act: -0.1700
Data Index: 3054841 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.1406. Min Act: -0.1700
Data Index: 3006753 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5156. Min Range: -7.5156
Max Act: 7.5156. Min Act: -0.1700
Data Index: 4316910 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.8906. Min Act: -0.1700
Data Index: 4895711 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5156. Min Range: -7.5156
Max Act: 6.8281. Min Act: -0.1700
Data Index: 4468296 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19