Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 542 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.2481. Min Act: -0.1700
Data Index: 2124316 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.1984. Min Act: -0.1700
Data Index: 8274159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.1485. Min Act: -0.1700
Data Index: 4245183 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.1318. Min Act: -0.1700
Data Index: 5474828 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0816. Min Act: -0.1700
Data Index: 8127464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0816. Min Act: -0.1700
Data Index: 5673721 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0480. Min Act: -0.1700
Data Index: 8742318 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0480. Min Act: -0.1700
Data Index: 2675451 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0480. Min Act: -0.1700
Data Index: 6910263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0312. Min Act: -0.1700
Data Index: 7145268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0312. Min Act: -0.1700
Data Index: 6836192 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0312. Min Act: -0.1700
Data Index: 1123414 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0143. Min Act: -0.1700
Data Index: 8787257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0143. Min Act: -0.1700
Data Index: 256524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0143. Min Act: -0.1700
Data Index: 8438875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2481. Min Range: -2.2481
Max Act: 2.0312. Min Act: -0.1700
Data Index: 3107391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2481. Min Range: -2.2481
Max Act: 1.9974. Min Act: -0.1700
Data Index: 2340707 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2481. Min Range: -2.2481
Max Act: 1.9974. Min Act: -0.1700
Data Index: 6135795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2481. Min Range: -2.2481
Max Act: 1.9974. Min Act: -0.1700
Data Index: 6930676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2481. Min Range: -2.2481
Max Act: 1.9974. Min Act: -0.1700
Data Index: 8400257 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19