Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1593 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3254. Min Range: -7.3254
Max Act: 7.3254. Min Act: -0.1700
Data Index: 1122840 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3254. Min Range: -7.3254
Max Act: 7.3254. Min Act: -0.1700
Data Index: 8197369 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3254. Min Range: -7.3254
Max Act: 7.0754. Min Act: -0.1700
Data Index: 874965 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3254. Min Range: -7.3254
Max Act: 7.0754. Min Act: -0.1700
Data Index: 6479089 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3254. Min Range: -7.3254
Max Act: 7.0129. Min Act: -0.1700
Data Index: 3314900 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3254. Min Range: -7.3254
Max Act: 7.0129. Min Act: -0.1700
Data Index: 3421123 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.9817. Min Act: -0.1700
Data Index: 2620377 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.8567. Min Act: -0.1700
Data Index: 4632172 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.8879. Min Act: -0.1700
Data Index: 4652238 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.8879. Min Act: -0.1700
Data Index: 763940 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.9192. Min Act: -0.1700
Data Index: 965156 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.8567. Min Act: -0.1700
Data Index: 5958573 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.8567. Min Act: -0.1700
Data Index: 5372235 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.8567. Min Act: -0.1700
Data Index: 6939074 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.8254. Min Act: -0.1700
Data Index: 626025 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.8567. Min Act: -0.1700
Data Index: 4447144 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.8254. Min Act: -0.1700
Data Index: 8471349 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.8254. Min Act: -0.1700
Data Index: 6627571 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.7942. Min Act: -0.1700
Data Index: 2533501 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3254. Min Range: -7.3254
Max Act: 6.7942. Min Act: -0.1700
Data Index: 1807596 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19