Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4958 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.6761. Min Act: -0.1700
Data Index: 2872393 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.5198. Min Act: -0.1700
Data Index: 2847744 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.4886. Min Act: -0.1700
Data Index: 6837196 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.3948. Min Act: -0.1700
Data Index: 4865043 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.2698. Min Act: -0.1700
Data Index: 557684 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.1761. Min Act: -0.1700
Data Index: 3356702 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.1448. Min Act: -0.1700
Data Index: 7025672 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.0823. Min Act: -0.1700
Data Index: 2106700 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.0511. Min Act: -0.1700
Data Index: 6272093 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.1136. Min Act: -0.1700
Data Index: 8646285 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.0511. Min Act: -0.1700
Data Index: 5027379 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.0511. Min Act: -0.1700
Data Index: 1846650 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.0198. Min Act: -0.1700
Data Index: 7481499 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6761. Min Range: -7.6761
Max Act: 6.9886. Min Act: -0.1700
Data Index: 7097855 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6761. Min Range: -7.6761
Max Act: 7.0198. Min Act: -0.1700
Data Index: 5005085 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6761. Min Range: -7.6761
Max Act: 6.9886. Min Act: -0.1700
Data Index: 7531338 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6761. Min Range: -7.6761
Max Act: 6.9886. Min Act: -0.1700
Data Index: 1801087 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6761. Min Range: -7.6761
Max Act: 6.9573. Min Act: -0.1700
Data Index: 393076 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6761. Min Range: -7.6761
Max Act: 6.9261. Min Act: -0.1700
Data Index: 4780863 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6761. Min Range: -7.6761
Max Act: 6.9261. Min Act: -0.1700
Data Index: 8611363 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19