Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 706 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.7108. Min Act: -0.1700
Data Index: 650302 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.6482. Min Act: -0.1700
Data Index: 3789381 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.6169. Min Act: -0.1700
Data Index: 1013751 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.6169. Min Act: -0.1700
Data Index: 2683894 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.6169. Min Act: -0.1700
Data Index: 2445122 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.6169. Min Act: -0.1700
Data Index: 882583 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.6169. Min Act: -0.1700
Data Index: 447359 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5856. Min Act: -0.1700
Data Index: 7517338 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5856. Min Act: -0.1700
Data Index: 1353133 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5856. Min Act: -0.1700
Data Index: 8550593 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5700. Min Act: -0.1700
Data Index: 7256666 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5856. Min Act: -0.1700
Data Index: 4418341 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5543. Min Act: -0.1700
Data Index: 7643270 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5700. Min Act: -0.1700
Data Index: 4014763 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5387. Min Act: -0.1700
Data Index: 7683312 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5387. Min Act: -0.1700
Data Index: 6872553 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5543. Min Act: -0.1700
Data Index: 3918602 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5387. Min Act: -0.1700
Data Index: 7528727 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5543. Min Act: -0.1700
Data Index: 4417548 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7108. Min Range: -3.7108
Max Act: 3.5230. Min Act: -0.1700
Data Index: 1553525 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19