Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.3726. Min Act: -0.1700
Data Index: 6576965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.3101. Min Act: -0.1700
Data Index: 6593199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.3414. Min Act: -0.1700
Data Index: 2194910 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2476. Min Act: -0.1700
Data Index: 8120468 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2789. Min Act: -0.1700
Data Index: 760379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2789. Min Act: -0.1700
Data Index: 1579488 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2789. Min Act: -0.1700
Data Index: 4263400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2476. Min Act: -0.1700
Data Index: 3831603 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2164. Min Act: -0.1700
Data Index: 8115486 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2476. Min Act: -0.1700
Data Index: 395447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2164. Min Act: -0.1700
Data Index: 1917046 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2476. Min Act: -0.1700
Data Index: 4100665 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2476. Min Act: -0.1700
Data Index: 2433571 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2476. Min Act: -0.1700
Data Index: 1733351 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2476. Min Act: -0.1700
Data Index: 1577799 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2164. Min Act: -0.1700
Data Index: 4026568 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2164. Min Act: -0.1700
Data Index: 3959284 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2476. Min Act: -0.1700
Data Index: 3823878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.1851. Min Act: -0.1700
Data Index: 2736205 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3726. Min Range: -4.3726
Max Act: 4.2164. Min Act: -0.1700
Data Index: 3535048 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19