Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5040 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0124. Min Range: -7.0124
Max Act: 7.0124. Min Act: -0.1700
Data Index: 6294623 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.8874. Min Act: -0.1700
Data Index: 4655557 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.8249. Min Act: -0.1700
Data Index: 5020396 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.7936. Min Act: -0.1700
Data Index: 8632768 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.7311. Min Act: -0.1700
Data Index: 2074934 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.6999. Min Act: -0.1700
Data Index: 857107 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.6999. Min Act: -0.1700
Data Index: 4686064 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.6686. Min Act: -0.1700
Data Index: 804485 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.6686. Min Act: -0.1700
Data Index: 4119886 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.6374. Min Act: -0.1700
Data Index: 6337685 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.6374. Min Act: -0.1700
Data Index: 2060560 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.5749. Min Act: -0.1700
Data Index: 6689568 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.5749. Min Act: -0.1700
Data Index: 7712822 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.6061. Min Act: -0.1700
Data Index: 1129781 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.5749. Min Act: -0.1700
Data Index: 6881578 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.5436. Min Act: -0.1700
Data Index: 873767 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.5749. Min Act: -0.1700
Data Index: 3904750 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.5436. Min Act: -0.1700
Data Index: 5772175 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.5124. Min Act: -0.1700
Data Index: 3813159 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0124. Min Range: -7.0124
Max Act: 6.5436. Min Act: -0.1700
Data Index: 594668 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19