Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2861 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1442. Min Range: -6.1442
Max Act: 6.1442. Min Act: -0.1700
Data Index: 6835589 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.9880. Min Act: -0.1700
Data Index: 739429 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.9567. Min Act: -0.1700
Data Index: 7497315 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.9567. Min Act: -0.1700
Data Index: 3986191 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.9255. Min Act: -0.1700
Data Index: 1247707 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8942. Min Act: -0.1700
Data Index: 4013012 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8942. Min Act: -0.1700
Data Index: 5475096 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 2384853 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 6221193 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8942. Min Act: -0.1700
Data Index: 3129120 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 2715409 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 7230339 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 5156940 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8630. Min Act: -0.1700
Data Index: 5704581 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8317. Min Act: -0.1700
Data Index: 1212000 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8317. Min Act: -0.1700
Data Index: 7141005 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8317. Min Act: -0.1700
Data Index: 7575465 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8317. Min Act: -0.1700
Data Index: 1325182 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8005. Min Act: -0.1700
Data Index: 7356206 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1442. Min Range: -6.1442
Max Act: 5.8005. Min Act: -0.1700
Data Index: 4157429 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19