Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2683 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.8356. Min Act: -0.1700
Data Index: 3155853 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7418. Min Act: -0.1700
Data Index: 5311397 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7418. Min Act: -0.1700
Data Index: 1272575 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7731. Min Act: -0.1700
Data Index: 8461785 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7731. Min Act: -0.1700
Data Index: 4363791 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7731. Min Act: -0.1699
Data Index: 6968073 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7731. Min Act: -0.1700
Data Index: 6376417 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7731. Min Act: -0.1700
Data Index: 777817 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7418. Min Act: -0.1700
Data Index: 39076 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7105. Min Act: -0.1700
Data Index: 591598 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7105. Min Act: -0.1697
Data Index: 5302418 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7105. Min Act: -0.1700
Data Index: 1148159 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7418. Min Act: -0.1697
Data Index: 3240741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7418. Min Act: -0.1700
Data Index: 16568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7105. Min Act: -0.1700
Data Index: 314983 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7105. Min Act: -0.1700
Data Index: 3052388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7105. Min Act: -0.1699
Data Index: 2393725 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7418. Min Act: -0.1700
Data Index: 381904 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7105. Min Act: -0.1700
Data Index: 3657192 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8356. Min Range: -3.8356
Max Act: 3.7418. Min Act: -0.1700
Data Index: 1394696 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19