Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.3417. Min Act: -0.1700
Data Index: 7346158 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.3241. Min Act: -0.1700
Data Index: 5460421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.3064. Min Act: -0.1700
Data Index: 8195245 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.2535. Min Act: -0.1700
Data Index: 3073862 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.2447. Min Act: -0.1700
Data Index: 8785255 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.2271. Min Act: -0.1700
Data Index: 6699412 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.2447. Min Act: -0.1700
Data Index: 5586162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.2271. Min Act: -0.1700
Data Index: 1898755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.2271. Min Act: -0.1700
Data Index: 622092 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.2095. Min Act: -0.1700
Data Index: 1815895 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.2095. Min Act: -0.1700
Data Index: 544205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.1919. Min Act: -0.1700
Data Index: 8382615 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.1831. Min Act: -0.1700
Data Index: 696249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.1831. Min Act: -0.1700
Data Index: 6345361 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.1831. Min Act: -0.1700
Data Index: 8033551 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.1743. Min Act: -0.1700
Data Index: 669432 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.1743. Min Act: -0.1700
Data Index: 362121 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.1655. Min Act: -0.1699
Data Index: 3168409 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.1567. Min Act: -0.1699
Data Index: 2161333 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3417. Min Range: -1.3417
Max Act: 1.1567. Min Act: -0.1700
Data Index: 3556724 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19