Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4756 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.7874. Min Act: -0.1700
Data Index: 8432505 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.5999. Min Act: -0.1700
Data Index: 7727035 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.4437. Min Act: -0.1700
Data Index: 8432504 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.4437. Min Act: -0.1700
Data Index: 3652039 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.4124. Min Act: -0.1700
Data Index: 869050 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.3499. Min Act: -0.1700
Data Index: 2521374 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.3187. Min Act: -0.1700
Data Index: 7006543 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.3187. Min Act: -0.1700
Data Index: 5842209 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.3187. Min Act: -0.1700
Data Index: 1246744 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.3187. Min Act: -0.1700
Data Index: 4030342 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.3187. Min Act: -0.1700
Data Index: 8526852 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.2874. Min Act: -0.1700
Data Index: 6468095 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.2874. Min Act: -0.1700
Data Index: 909244 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.2874. Min Act: -0.1700
Data Index: 7341753 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.2874. Min Act: -0.1700
Data Index: 3462858 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.2249. Min Act: -0.1700
Data Index: 4539731 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.2562. Min Act: -0.1700
Data Index: 7734154 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.2562. Min Act: -0.1700
Data Index: 4875061 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.2249. Min Act: -0.1700
Data Index: 569409 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7874. Min Range: -5.7874
Max Act: 5.2562. Min Act: -0.1700
Data Index: 5195005 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19