Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.4020. Min Act: -0.1700
Data Index: 3265135 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.3236. Min Act: -0.1700
Data Index: 5473329 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.2922. Min Act: -0.1700
Data Index: 6005162 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.2765. Min Act: -0.1700
Data Index: 7033366 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.2451. Min Act: -0.1700
Data Index: 6553263 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.2294. Min Act: -0.1700
Data Index: 5960406 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.2137. Min Act: -0.1700
Data Index: 4409698 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1979. Min Act: -0.1700
Data Index: 7589775 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1979. Min Act: -0.1700
Data Index: 7863989 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1822. Min Act: -0.1700
Data Index: 6924638 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1665. Min Act: -0.1700
Data Index: 4687003 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1665. Min Act: -0.1700
Data Index: 6144714 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1665. Min Act: -0.1700
Data Index: 2620530 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1507. Min Act: -0.1700
Data Index: 8775869 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1665. Min Act: -0.1700
Data Index: 278688 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1507. Min Act: -0.1700
Data Index: 1326822 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1507. Min Act: -0.1700
Data Index: 6653669 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1665. Min Act: -0.1700
Data Index: 3219163 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1507. Min Act: -0.1700
Data Index: 7629993 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4020. Min Range: -3.4020
Max Act: 3.1507. Min Act: -0.1700
Data Index: 6109792 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19