Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.3153. Min Act: -0.1700
Data Index: 5370964 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.3153. Min Act: -0.1700
Data Index: 5634766 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.2840. Min Act: -0.1700
Data Index: 663049 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.2528. Min Act: -0.1700
Data Index: 6607886 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.2528. Min Act: -0.1700
Data Index: 3647781 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.2215. Min Act: -0.1700
Data Index: 925600 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.2215. Min Act: -0.1700
Data Index: 8177251 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.1903. Min Act: -0.1700
Data Index: 3109363 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.1903. Min Act: -0.1700
Data Index: 1734940 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.1903. Min Act: -0.1700
Data Index: 720736 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.2215. Min Act: -0.1700
Data Index: 895158 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.1590. Min Act: -0.1700
Data Index: 3072601 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.0965. Min Act: -0.1700
Data Index: 3196409 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.1278. Min Act: -0.1700
Data Index: 8552922 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.0965. Min Act: -0.1700
Data Index: 3420276 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.1278. Min Act: -0.1700
Data Index: 3608895 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.0965. Min Act: -0.1700
Data Index: 2162371 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.0965. Min Act: -0.1700
Data Index: 4052522 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.0965. Min Act: -0.1700
Data Index: 4470604 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3153. Min Range: -5.3153
Max Act: 5.0965. Min Act: -0.1700
Data Index: 3574240 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19