Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3877 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3107. Min Range: -6.3107
Max Act: 6.3107. Min Act: -0.1700
Data Index: 496534 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3107. Min Range: -6.3107
Max Act: 6.2795. Min Act: -0.1700
Data Index: 2846180 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3107. Min Range: -6.3107
Max Act: 6.2795. Min Act: -0.1700
Data Index: 8651432 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3107. Min Range: -6.3107
Max Act: 6.1232. Min Act: -0.1700
Data Index: 4470981 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3107. Min Range: -6.3107
Max Act: 6.1232. Min Act: -0.1700
Data Index: 219807 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3107. Min Range: -6.3107
Max Act: 6.0607. Min Act: -0.1700
Data Index: 272920 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3107. Min Range: -6.3107
Max Act: 6.0607. Min Act: -0.1700
Data Index: 8067956 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3107. Min Range: -6.3107
Max Act: 6.0607. Min Act: -0.1699
Data Index: 1884597 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9982. Min Act: -0.1700
Data Index: 651915 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9982. Min Act: -0.1700
Data Index: 5532943 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9982. Min Act: -0.1700
Data Index: 5318509 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9982. Min Act: -0.1697
Data Index: 6282765 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9357. Min Act: -0.1700
Data Index: 4275430 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9982. Min Act: -0.1700
Data Index: 4340071 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9670. Min Act: -0.1700
Data Index: 2163121 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9670. Min Act: -0.1700
Data Index: 2937426 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9670. Min Act: -0.1700
Data Index: 7435561 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9670. Min Act: -0.1700
Data Index: 657184 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9670. Min Act: -0.1700
Data Index: 1910240 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3107. Min Range: -6.3107
Max Act: 5.9357. Min Act: -0.1700
Data Index: 6965260 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19