Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1656. Min Range: -6.1656
Max Act: 6.1656. Min Act: -0.1700
Data Index: 5749186 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.9468. Min Act: -0.1700
Data Index: 6232044 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.8843. Min Act: -0.1700
Data Index: 1380329 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.8218. Min Act: -0.1700
Data Index: 616 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.7593. Min Act: -0.1700
Data Index: 4566675 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.6968. Min Act: -0.1700
Data Index: 4067189 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.6656. Min Act: -0.1700
Data Index: 819500 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.6656. Min Act: -0.1700
Data Index: 8369286 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.6968. Min Act: -0.1700
Data Index: 3666301 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.6031. Min Act: -0.1700
Data Index: 6519328 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.5406. Min Act: -0.1700
Data Index: 8409277 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.5093. Min Act: -0.1700
Data Index: 6242056 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.5093. Min Act: -0.1700
Data Index: 3145710 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.4781. Min Act: -0.1700
Data Index: 1593372 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.5093. Min Act: -0.1700
Data Index: 3092525 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.4781. Min Act: -0.1700
Data Index: 930071 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.4781. Min Act: -0.1700
Data Index: 7905211 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.4781. Min Act: -0.1700
Data Index: 8069305 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.5093. Min Act: -0.1700
Data Index: 3976378 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1656. Min Range: -6.1656
Max Act: 5.4781. Min Act: -0.1700
Data Index: 5841280 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19