Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4893 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.6122. Min Act: -0.1700
Data Index: 4423866 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.5965. Min Act: -0.1700
Data Index: 8022848 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.5652. Min Act: -0.1700
Data Index: 819481 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.5652. Min Act: -0.1700
Data Index: 6902048 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.5496. Min Act: -0.1700
Data Index: 6908815 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.5496. Min Act: -0.1700
Data Index: 7587183 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.5182. Min Act: -0.1700
Data Index: 1627061 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4869. Min Act: -0.1700
Data Index: 5389796 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4869. Min Act: -0.1700
Data Index: 7998507 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4713. Min Act: -0.1700
Data Index: 444890 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4713. Min Act: -0.1700
Data Index: 1923233 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4242. Min Act: -0.1700
Data Index: 2736400 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4399. Min Act: -0.1700
Data Index: 4297850 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4399. Min Act: -0.1700
Data Index: 4807110 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4242. Min Act: -0.1700
Data Index: 5404155 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4242. Min Act: -0.1700
Data Index: 4419356 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4242. Min Act: -0.1700
Data Index: 2931602 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.4242. Min Act: -0.1700
Data Index: 723326 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.3772. Min Act: -0.1700
Data Index: 1508754 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6122. Min Range: -3.6122
Max Act: 3.3772. Min Act: -0.1700
Data Index: 3547323 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19