Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1938 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7343. Min Range: -9.7343
Max Act: 9.7343. Min Act: -0.1700
Data Index: 1033215 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7343. Min Range: -9.7343
Max Act: 9.6718. Min Act: -0.1700
Data Index: 8262774 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7343. Min Range: -9.7343
Max Act: 9.3593. Min Act: -0.1700
Data Index: 3417758 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7343. Min Range: -9.7343
Max Act: 9.3593. Min Act: -0.1700
Data Index: 3755887 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7343. Min Range: -9.7343
Max Act: 9.2968. Min Act: -0.1700
Data Index: 2414537 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7343. Min Range: -9.7343
Max Act: 9.2343. Min Act: -0.1700
Data Index: 2771603 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7343. Min Range: -9.7343
Max Act: 9.2343. Min Act: -0.1700
Data Index: 3134157 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7343. Min Range: -9.7343
Max Act: 9.1093. Min Act: -0.1700
Data Index: 7095514 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7343. Min Range: -9.7343
Max Act: 9.0468. Min Act: -0.1700
Data Index: 6736532 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7343. Min Range: -9.7343
Max Act: 8.9843. Min Act: -0.1700
Data Index: 6467992 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7343. Min Range: -9.7343
Max Act: 9.0468. Min Act: -0.1700
Data Index: 2017832 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7343. Min Range: -9.7343
Max Act: 8.9218. Min Act: -0.1700
Data Index: 3714084 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7343. Min Range: -9.7343
Max Act: 8.9218. Min Act: -0.1700
Data Index: 810752 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7343. Min Range: -9.7343
Max Act: 8.8593. Min Act: -0.1700
Data Index: 3412102 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7343. Min Range: -9.7343
Max Act: 8.8593. Min Act: -0.1700
Data Index: 4918046 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7343. Min Range: -9.7343
Max Act: 8.7968. Min Act: -0.1700
Data Index: 4064293 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7343. Min Range: -9.7343
Max Act: 8.7343. Min Act: -0.1700
Data Index: 594050 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7343. Min Range: -9.7343
Max Act: 8.6718. Min Act: -0.1700
Data Index: 1407898 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7343. Min Range: -9.7343
Max Act: 8.6093. Min Act: -0.1700
Data Index: 6318567 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7343. Min Range: -9.7343
Max Act: 8.6093. Min Act: -0.1700
Data Index: 1985267 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19