Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4524 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3215. Min Range: -8.3215
Max Act: 8.3215. Min Act: -0.1700
Data Index: 1610321 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3215. Min Range: -8.3215
Max Act: 8.0715. Min Act: -0.1700
Data Index: 8300300 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.9465. Min Act: -0.1700
Data Index: 5356827 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.9465. Min Act: -0.1700
Data Index: 1989220 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.8840. Min Act: -0.1700
Data Index: 7245776 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.8527. Min Act: -0.1700
Data Index: 453783 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.8215. Min Act: -0.1700
Data Index: 1342395 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.8215. Min Act: -0.1700
Data Index: 8231214 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.8215. Min Act: -0.1700
Data Index: 2263605 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.8527. Min Act: -0.1700
Data Index: 5200925 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.7590. Min Act: -0.1700
Data Index: 4981863 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.7902. Min Act: -0.1700
Data Index: 8445422 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.7590. Min Act: -0.1700
Data Index: 4645801 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.7590. Min Act: -0.1700
Data Index: 5435210 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.6965. Min Act: -0.1700
Data Index: 5235185 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.7277. Min Act: -0.1700
Data Index: 6343685 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.7277. Min Act: -0.1700
Data Index: 8634134 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.7277. Min Act: -0.1700
Data Index: 6498146 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.7277. Min Act: -0.1700
Data Index: 3247698 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3215. Min Range: -8.3215
Max Act: 7.6965. Min Act: -0.1700
Data Index: 979536 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19