Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 558 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.6565. Min Act: -0.1700
Data Index: 1978518 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.6252. Min Act: -0.1700
Data Index: 7976758 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.5000. Min Act: -0.1700
Data Index: 4406594 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.4530. Min Act: -0.1700
Data Index: 2993913 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.4373. Min Act: -0.1700
Data Index: 5416272 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.4373. Min Act: -0.1700
Data Index: 4663578 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.4060. Min Act: -0.1700
Data Index: 4100620 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.4216. Min Act: -0.1700
Data Index: 5537403 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3903. Min Act: -0.1700
Data Index: 4053052 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.4060. Min Act: -0.1700
Data Index: 3423777 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3903. Min Act: -0.1700
Data Index: 3203903 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3903. Min Act: -0.1700
Data Index: 7730686 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.4216. Min Act: -0.1700
Data Index: 2202911 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.4060. Min Act: -0.1700
Data Index: 7559567 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3746. Min Act: -0.1700
Data Index: 7957919 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3903. Min Act: -0.1700
Data Index: 7156300 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3903. Min Act: -0.1700
Data Index: 6484653 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3903. Min Act: -0.1700
Data Index: 2371848 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3589. Min Act: -0.1700
Data Index: 2416636 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6565. Min Range: -3.6565
Max Act: 3.3903. Min Act: -0.1700
Data Index: 83680 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19