Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1769. Min Range: -6.1769
Max Act: 6.1769. Min Act: -0.1700
Data Index: 356191 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1769. Min Range: -6.1769
Max Act: 6.0832. Min Act: -0.1700
Data Index: 7531562 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1769. Min Range: -6.1769
Max Act: 6.0832. Min Act: -0.1700
Data Index: 1258884 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1769. Min Range: -6.1769
Max Act: 6.0207. Min Act: -0.1700
Data Index: 1105339 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1769. Min Range: -6.1769
Max Act: 6.0207. Min Act: -0.1700
Data Index: 96793 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.9894. Min Act: -0.1700
Data Index: 113143 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.9582. Min Act: -0.1700
Data Index: 96797 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.9894. Min Act: -0.1700
Data Index: 2811174 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.9582. Min Act: -0.1700
Data Index: 8530979 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.8957. Min Act: -0.1700
Data Index: 3303587 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.8957. Min Act: -0.1700
Data Index: 4501451 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.8019. Min Act: -0.1700
Data Index: 3448020 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.8019. Min Act: -0.1700
Data Index: 3448025 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.8019. Min Act: -0.1700
Data Index: 4360305 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.8332. Min Act: -0.1700
Data Index: 1105341 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.8019. Min Act: -0.1700
Data Index: 87205 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.7707. Min Act: -0.1700
Data Index: 5840294 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.7707. Min Act: -0.1700
Data Index: 5318661 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.7707. Min Act: -0.1700
Data Index: 7879474 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1769. Min Range: -6.1769
Max Act: 5.7707. Min Act: -0.1700
Data Index: 4360308 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19