Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4606. Min Range: -7.4606
Max Act: 7.4606. Min Act: -0.1700
Data Index: 1303993 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4606. Min Range: -7.4606
Max Act: 7.2731. Min Act: -0.1700
Data Index: 2531603 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4606. Min Range: -7.4606
Max Act: 7.2106. Min Act: -0.1700
Data Index: 2776716 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4606. Min Range: -7.4606
Max Act: 7.0856. Min Act: -0.1700
Data Index: 7578711 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4606. Min Range: -7.4606
Max Act: 7.0543. Min Act: -0.1700
Data Index: 1287308 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4606. Min Range: -7.4606
Max Act: 7.0856. Min Act: -0.1700
Data Index: 5129538 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4606. Min Range: -7.4606
Max Act: 7.0543. Min Act: -0.1700
Data Index: 3614347 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.9918. Min Act: -0.1700
Data Index: 7523978 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4606. Min Range: -7.4606
Max Act: 7.0231. Min Act: -0.1700
Data Index: 1989071 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.9918. Min Act: -0.1700
Data Index: 57787 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.9606. Min Act: -0.1700
Data Index: 6452022 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.9606. Min Act: -0.1700
Data Index: 1291145 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.9606. Min Act: -0.1700
Data Index: 5929239 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.8981. Min Act: -0.1700
Data Index: 4447406 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.9293. Min Act: -0.1700
Data Index: 1303588 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.8981. Min Act: -0.1700
Data Index: 7214052 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.8981. Min Act: -0.1700
Data Index: 2887959 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.8981. Min Act: -0.1700
Data Index: 2581000 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.8981. Min Act: -0.1700
Data Index: 3610048 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4606. Min Range: -7.4606
Max Act: 6.8668. Min Act: -0.1700
Data Index: 2261664 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19