Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1293 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 3670791 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 6595827 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 1345723 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 2149398 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 6737005 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 4100568 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 2149399 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 4414727 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 5477459 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 3702655 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 2530961 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 3293251 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 5059343 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 1670306 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 3666413 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 6519089 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 1570160 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 5477465 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 1570159 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4194. Min Range: -2.4194
Max Act: 2.4194. Min Act: -0.1700
Data Index: 4132385 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19