Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1320 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.9011. Min Act: -0.1700
Data Index: 1764094 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.8693. Min Act: -0.1700
Data Index: 8010594 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.8217. Min Act: -0.1700
Data Index: 1342374 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.8376. Min Act: -0.1700
Data Index: 219332 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7739. Min Act: -0.1700
Data Index: 8820592 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7898. Min Act: -0.1700
Data Index: 5408612 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7420. Min Act: -0.1700
Data Index: 6848606 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7579. Min Act: -0.1700
Data Index: 2191043 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7579. Min Act: -0.1700
Data Index: 2651669 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7420. Min Act: -0.1700
Data Index: 292165 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7420. Min Act: -0.1700
Data Index: 7943683 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7579. Min Act: -0.1700
Data Index: 2209060 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7420. Min Act: -0.1700
Data Index: 2894762 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7260. Min Act: -0.1700
Data Index: 188816 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7420. Min Act: -0.1700
Data Index: 4230676 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7100. Min Act: -0.1700
Data Index: 7724157 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7100. Min Act: -0.1700
Data Index: 8820591 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7260. Min Act: -0.1700
Data Index: 5310059 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7260. Min Act: -0.1700
Data Index: 3219385 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9011. Min Range: -2.9011
Max Act: 2.7260. Min Act: -0.1700
Data Index: 4379330 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19