Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.5489. Min Range: -14.5489
Max Act: 14.5489. Min Act: -0.1700
Data Index: 4391133 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.5489. Min Range: -14.5489
Max Act: 14.3614. Min Act: -0.1700
Data Index: 1612341 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.5489. Min Range: -14.5489
Max Act: 14.1739. Min Act: -0.1700
Data Index: 6579650 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.9239. Min Act: -0.1700
Data Index: 7515284 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.6739. Min Act: -0.1700
Data Index: 3812473 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.6739. Min Act: -0.1700
Data Index: 5191823 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.6739. Min Act: -0.1700
Data Index: 5931918 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.4864. Min Act: -0.1700
Data Index: 1625464 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.4239. Min Act: -0.1700
Data Index: 3554074 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.3614. Min Act: -0.1700
Data Index: 4005093 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.3614. Min Act: -0.1700
Data Index: 4366368 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.3614. Min Act: -0.1700
Data Index: 7799374 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.3614. Min Act: -0.1700
Data Index: 2230192 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.3614. Min Act: -0.1700
Data Index: 1247523 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.2364. Min Act: -0.1700
Data Index: 5794236 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.2364. Min Act: -0.1700
Data Index: 2219614 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.2989. Min Act: -0.1700
Data Index: 4274942 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.1114. Min Act: -0.1700
Data Index: 6589249 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.1739. Min Act: -0.1696
Data Index: 5115048 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.5489. Min Range: -14.5489
Max Act: 13.2364. Min Act: -0.1700
Data Index: 4024913 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19