Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 974 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0703. Min Range: -8.0703
Max Act: 8.0703. Min Act: -0.1700
Data Index: 2729134 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0703. Min Range: -8.0703
Max Act: 7.4765. Min Act: -0.1700
Data Index: 817171 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0703. Min Range: -8.0703
Max Act: 7.4765. Min Act: -0.1700
Data Index: 4398855 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0703. Min Range: -8.0703
Max Act: 7.4765. Min Act: -0.1700
Data Index: 459965 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0703. Min Range: -8.0703
Max Act: 7.4140. Min Act: -0.1700
Data Index: 5251429 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0703. Min Range: -8.0703
Max Act: 7.4140. Min Act: -0.1700
Data Index: 8362570 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0703. Min Range: -8.0703
Max Act: 7.1640. Min Act: -0.1700
Data Index: 6017446 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0703. Min Range: -8.0703
Max Act: 7.1328. Min Act: -0.1700
Data Index: 2533096 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0703. Min Range: -8.0703
Max Act: 7.0078. Min Act: -0.1700
Data Index: 4675915 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.9765. Min Act: -0.1700
Data Index: 1285905 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.9453. Min Act: -0.1700
Data Index: 2248012 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.8515. Min Act: -0.1700
Data Index: 8832810 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.7890. Min Act: -0.1700
Data Index: 2890575 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.7578. Min Act: -0.1700
Data Index: 5071243 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.7578. Min Act: -0.1700
Data Index: 6789665 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.6953. Min Act: -0.1700
Data Index: 912269 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.6953. Min Act: -0.1700
Data Index: 4600169 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.6328. Min Act: -0.1700
Data Index: 7795755 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.6640. Min Act: -0.1700
Data Index: 2386423 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0703. Min Range: -8.0703
Max Act: 6.6328. Min Act: -0.1700
Data Index: 7629901 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19