Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.2719. Min Act: -0.1700
Data Index: 5107796 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.2406. Min Act: -0.1694
Data Index: 5075899 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.2094. Min Act: -0.1700
Data Index: 4185253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.1781. Min Act: -0.1700
Data Index: 4267424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.1469. Min Act: -0.1700
Data Index: 4788501 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.1156. Min Act: -0.1700
Data Index: 1811068 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.1156. Min Act: -0.1700
Data Index: 4858177 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.1156. Min Act: -0.1700
Data Index: 456986 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.1156. Min Act: -0.1700
Data Index: 7842198 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.1156. Min Act: -0.1700
Data Index: 2201546 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.1156. Min Act: -0.1700
Data Index: 6539255 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.1156. Min Act: -0.1700
Data Index: 6283850 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.1156. Min Act: -0.1700
Data Index: 7257533 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0844. Min Act: -0.1700
Data Index: 2121428 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0844. Min Act: -0.1700
Data Index: 2105588 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0844. Min Act: -0.1700
Data Index: 2351446 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0531. Min Act: -0.1697
Data Index: 2417224 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0531. Min Act: -0.1700
Data Index: 361706 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0531. Min Act: -0.1700
Data Index: 528005 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2719. Min Range: -5.2719
Max Act: 5.0531. Min Act: -0.1700
Data Index: 2800986 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19