Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1200. Min Range: -5.1200
Max Act: 5.1200. Min Act: -0.1700
Data Index: 5672632 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1200. Min Range: -5.1200
Max Act: 5.0575. Min Act: -0.1700
Data Index: 2703303 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9638. Min Act: -0.1700
Data Index: 4552902 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9013. Min Act: -0.1700
Data Index: 2135580 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.9013. Min Act: -0.1700
Data Index: 5702117 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.8700. Min Act: -0.1700
Data Index: 6965105 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.8075. Min Act: -0.1700
Data Index: 3582112 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7763. Min Act: -0.1700
Data Index: 8542831 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7763. Min Act: -0.1700
Data Index: 7975382 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7763. Min Act: -0.1700
Data Index: 4356433 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7763. Min Act: -0.1700
Data Index: 292959 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7763. Min Act: -0.1700
Data Index: 5718488 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7450. Min Act: -0.1700
Data Index: 5663682 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7450. Min Act: -0.1700
Data Index: 7753349 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7138. Min Act: -0.1700
Data Index: 8598819 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7138. Min Act: -0.1700
Data Index: 6745123 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7138. Min Act: -0.1700
Data Index: 5682741 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7138. Min Act: -0.1700
Data Index: 5084058 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7138. Min Act: -0.1700
Data Index: 7488179 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1200. Min Range: -5.1200
Max Act: 4.7138. Min Act: -0.1700
Data Index: 763456 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19