Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7999. Min Range: -6.7999
Max Act: 6.7999. Min Act: -0.1700
Data Index: 2704644 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7999. Min Range: -6.7999
Max Act: 6.3624. Min Act: -0.1700
Data Index: 569869 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7999. Min Range: -6.7999
Max Act: 6.2374. Min Act: -0.1700
Data Index: 5247683 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7999. Min Range: -6.7999
Max Act: 6.0187. Min Act: -0.1700
Data Index: 1343387 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.9562. Min Act: -0.1700
Data Index: 7785596 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.9249. Min Act: -0.1700
Data Index: 6437004 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.8624. Min Act: -0.1700
Data Index: 6391599 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.8624. Min Act: -0.1700
Data Index: 5585550 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.8312. Min Act: -0.1700
Data Index: 4164600 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.8312. Min Act: -0.1700
Data Index: 2858414 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.8312. Min Act: -0.1700
Data Index: 8431651 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.8624. Min Act: -0.1700
Data Index: 2107076 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.8312. Min Act: -0.1700
Data Index: 2140367 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.7999. Min Act: -0.1700
Data Index: 8120269 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.7999. Min Act: -0.1700
Data Index: 3758203 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.7687. Min Act: -0.1700
Data Index: 8471954 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.7687. Min Act: -0.1700
Data Index: 4139194 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.7062. Min Act: -0.1700
Data Index: 628211 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.7374. Min Act: -0.1700
Data Index: 1143107 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7999. Min Range: -6.7999
Max Act: 5.7687. Min Act: -0.1700
Data Index: 2310800 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19