Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.9294. Min Act: -0.1700
Data Index: 3150944 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.8818. Min Act: -0.1700
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.8501. Min Act: -0.1700
Data Index: 7465156 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.8183. Min Act: -0.1700
Data Index: 5040061 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.7386. Min Act: -0.1700
Data Index: 5402995 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.7386. Min Act: -0.1700
Data Index: 2964414 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.7386. Min Act: -0.1700
Data Index: 2044038 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.7226. Min Act: -0.1700
Data Index: 4021976 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.7066. Min Act: -0.1700
Data Index: 8511343 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.7066. Min Act: -0.1700
Data Index: 882880 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.7066. Min Act: -0.1700
Data Index: 463960 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.6906. Min Act: -0.1700
Data Index: 2282858 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.6906. Min Act: -0.1700
Data Index: 8074937 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.6746. Min Act: -0.1700
Data Index: 8074938 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.6906. Min Act: -0.1700
Data Index: 5772743 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.6906. Min Act: -0.1700
Data Index: 2881100 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.6746. Min Act: -0.1700
Data Index: 7647119 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.6746. Min Act: -0.1700
Data Index: 1015749 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.6746. Min Act: -0.1700
Data Index: 1350847 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9294. Min Range: -2.9294
Max Act: 2.6746. Min Act: -0.1700
Data Index: 5028997 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19