Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.6047. Min Act: -0.1699
Data Index: 1539539 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.4754. Min Act: -0.1700
Data Index: 7077560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.4754. Min Act: -0.1700
Data Index: 5699873 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.4267. Min Act: -0.1700
Data Index: 1168481 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.4267. Min Act: -0.1700
Data Index: 2739839 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.4104. Min Act: -0.1700
Data Index: 8440959 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.4104. Min Act: -0.1700
Data Index: 2662137 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.4104. Min Act: -0.1700
Data Index: 3927929 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3940. Min Act: -0.1700
Data Index: 3655434 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3777. Min Act: -0.1700
Data Index: 2039664 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3777. Min Act: -0.1700
Data Index: 1962445 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3613. Min Act: -0.1700
Data Index: 603879 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3450. Min Act: -0.1700
Data Index: 3810823 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3286. Min Act: -0.1700
Data Index: 2829056 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3286. Min Act: -0.1700
Data Index: 7542531 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3286. Min Act: -0.1700
Data Index: 2739838 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3286. Min Act: -0.1700
Data Index: 3244847 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3286. Min Act: -0.1700
Data Index: 607464 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3286. Min Act: -0.1700
Data Index: 3244844 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6047. Min Range: -2.6047
Max Act: 2.3286. Min Act: -0.1700
Data Index: 2039663 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19