Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3162 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.4109. Min Act: -0.1700
Data Index: 4217957 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.3952. Min Act: -0.1700
Data Index: 2304502 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.3481. Min Act: -0.1700
Data Index: 4067155 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.3795. Min Act: -0.1700
Data Index: 4051685 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.3638. Min Act: -0.1700
Data Index: 3663959 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.3638. Min Act: -0.1700
Data Index: 3185424 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.3324. Min Act: -0.1700
Data Index: 4000680 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.3324. Min Act: -0.1700
Data Index: 1240318 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.2854. Min Act: -0.1700
Data Index: 7377974 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.2697. Min Act: -0.1700
Data Index: 179578 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.3168. Min Act: -0.1700
Data Index: 4995322 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.2854. Min Act: -0.1700
Data Index: 5976189 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.3011. Min Act: -0.1700
Data Index: 8686355 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.2697. Min Act: -0.1700
Data Index: 197119 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.2854. Min Act: -0.1700
Data Index: 6031493 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.2697. Min Act: -0.1700
Data Index: 7074615 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.2225. Min Act: -0.1700
Data Index: 8427964 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.2225. Min Act: -0.1700
Data Index: 3397311 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.1911. Min Act: -0.1700
Data Index: 229822 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4109. Min Range: -3.4109
Max Act: 3.2068. Min Act: -0.1700
Data Index: 2875890 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19