Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3948 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.6163. Min Act: -0.1700
Data Index: 1320347 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.3350. Min Act: -0.1700
Data Index: 3301294 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.2725. Min Act: -0.1700
Data Index: 8650667 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.2413. Min Act: -0.1700
Data Index: 2583378 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.2413. Min Act: -0.1700
Data Index: 2471051 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.1788. Min Act: -0.1700
Data Index: 2685110 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.1475. Min Act: -0.1700
Data Index: 6430594 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.1475. Min Act: -0.1700
Data Index: 7513930 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.1475. Min Act: -0.1700
Data Index: 5941859 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.1163. Min Act: -0.1700
Data Index: 8411776 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.1163. Min Act: -0.1700
Data Index: 898189 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.1163. Min Act: -0.1700
Data Index: 4272676 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.1163. Min Act: -0.1700
Data Index: 3154447 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.0850. Min Act: -0.1700
Data Index: 7147006 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.0850. Min Act: -0.1700
Data Index: 2606560 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6163. Min Range: -7.6163
Max Act: 7.0225. Min Act: -0.1700
Data Index: 2258602 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6163. Min Range: -7.6163
Max Act: 6.9913. Min Act: -0.1700
Data Index: 3948426 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6163. Min Range: -7.6163
Max Act: 6.9913. Min Act: -0.1700
Data Index: 1934168 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6163. Min Range: -7.6163
Max Act: 6.9913. Min Act: -0.1700
Data Index: 6310288 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6163. Min Range: -7.6163
Max Act: 6.9913. Min Act: -0.1700
Data Index: 3166130 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19