Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2286 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9103. Min Range: -9.9103
Max Act: 9.9103. Min Act: -0.1700
Data Index: 1271031 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9103. Min Range: -9.9103
Max Act: 9.5353. Min Act: -0.1700
Data Index: 228493 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9103. Min Range: -9.9103
Max Act: 9.4728. Min Act: -0.1700
Data Index: 4173266 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9103. Min Range: -9.9103
Max Act: 9.4103. Min Act: -0.1700
Data Index: 8486970 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9103. Min Range: -9.9103
Max Act: 9.4103. Min Act: -0.1700
Data Index: 4639956 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9103. Min Range: -9.9103
Max Act: 9.3478. Min Act: -0.1700
Data Index: 3279245 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9103. Min Range: -9.9103
Max Act: 9.2228. Min Act: -0.1700
Data Index: 6171421 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9103. Min Range: -9.9103
Max Act: 9.0978. Min Act: -0.1700
Data Index: 7809476 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9103. Min Range: -9.9103
Max Act: 9.1603. Min Act: -0.1700
Data Index: 4806016 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9103. Min Range: -9.9103
Max Act: 9.0353. Min Act: -0.1700
Data Index: 7175002 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9103. Min Range: -9.9103
Max Act: 8.9103. Min Act: -0.1700
Data Index: 308915 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9103. Min Range: -9.9103
Max Act: 8.9728. Min Act: -0.1700
Data Index: 5000849 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9103. Min Range: -9.9103
Max Act: 8.9728. Min Act: -0.1700
Data Index: 6461426 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9103. Min Range: -9.9103
Max Act: 8.9728. Min Act: -0.1700
Data Index: 2789531 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9103. Min Range: -9.9103
Max Act: 8.9103. Min Act: -0.1700
Data Index: 7695399 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9103. Min Range: -9.9103
Max Act: 8.9103. Min Act: -0.1700
Data Index: 3908835 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9103. Min Range: -9.9103
Max Act: 8.9103. Min Act: -0.1700
Data Index: 6192776 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9103. Min Range: -9.9103
Max Act: 8.9728. Min Act: -0.1700
Data Index: 7074942 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9103. Min Range: -9.9103
Max Act: 8.9103. Min Act: -0.1700
Data Index: 6566262 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9103. Min Range: -9.9103
Max Act: 8.9728. Min Act: -0.1700
Data Index: 3976726 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19