Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2443 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.3283. Min Act: -0.1700
Data Index: 5832073 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.3283. Min Act: -0.1700
Data Index: 5144449 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.2658. Min Act: -0.1700
Data Index: 8443050 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.2345. Min Act: -0.1700
Data Index: 3347560 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.2345. Min Act: -0.1700
Data Index: 2294635 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.2032. Min Act: -0.1700
Data Index: 5389627 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.1720. Min Act: -0.1700
Data Index: 1619516 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.1095. Min Act: -0.1700
Data Index: 7408693 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.1095. Min Act: -0.1700
Data Index: 8093123 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.0470. Min Act: -0.1700
Data Index: 7560679 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.0782. Min Act: -0.1700
Data Index: 2099646 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.0782. Min Act: -0.1700
Data Index: 1917555 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.0470. Min Act: -0.1700
Data Index: 4473949 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.0782. Min Act: -0.1700
Data Index: 5954746 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.0157. Min Act: -0.1700
Data Index: 6256568 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.0157. Min Act: -0.1700
Data Index: 7596825 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3283. Min Range: -4.3283
Max Act: 4.0157. Min Act: -0.1700
Data Index: 6111738 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3283. Min Range: -4.3283
Max Act: 3.9688. Min Act: -0.1700
Data Index: 5779382 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3283. Min Range: -4.3283
Max Act: 3.9844. Min Act: -0.1700
Data Index: 4760937 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3283. Min Range: -4.3283
Max Act: 3.9376. Min Act: -0.1700
Data Index: 4861060 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19