Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4239 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0268. Min Range: -7.0268
Max Act: 7.0268. Min Act: -0.1700
Data Index: 8760392 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.9643. Min Act: -0.1700
Data Index: 4231995 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.9018. Min Act: -0.1700
Data Index: 1199031 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.8081. Min Act: -0.1700
Data Index: 5329222 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.7143. Min Act: -0.1700
Data Index: 4795650 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.7143. Min Act: -0.1700
Data Index: 8297361 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.7143. Min Act: -0.1700
Data Index: 4285004 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.7143. Min Act: -0.1700
Data Index: 3569150 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.6518. Min Act: -0.1700
Data Index: 3543135 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.6831. Min Act: -0.1700
Data Index: 3103531 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.6831. Min Act: -0.1700
Data Index: 7483231 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.6518. Min Act: -0.1700
Data Index: 1488451 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.6518. Min Act: -0.1700
Data Index: 8692250 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.6206. Min Act: -0.1700
Data Index: 800116 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.6206. Min Act: -0.1700
Data Index: 3276297 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.6206. Min Act: -0.1700
Data Index: 780193 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.6206. Min Act: -0.1700
Data Index: 7579021 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.5893. Min Act: -0.1700
Data Index: 4168168 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.5581. Min Act: -0.1700
Data Index: 3638654 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0268. Min Range: -7.0268
Max Act: 6.5268. Min Act: -0.1700
Data Index: 2576306 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19