Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3353 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.3588. Min Act: -0.1700
Data Index: 7105368 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2963. Min Act: -0.1700
Data Index: 3740713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2963. Min Act: -0.1700
Data Index: 5113510 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2650. Min Act: -0.1700
Data Index: 6559187 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2963. Min Act: -0.1700
Data Index: 2847044 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2963. Min Act: -0.1700
Data Index: 8760628 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2963. Min Act: -0.1700
Data Index: 3345551 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2963. Min Act: -0.1700
Data Index: 3599841 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2963. Min Act: -0.1700
Data Index: 4656395 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2963. Min Act: -0.1700
Data Index: 3791982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2963. Min Act: -0.1700
Data Index: 1523229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2338. Min Act: -0.1700
Data Index: 4169561 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2650. Min Act: -0.1700
Data Index: 1671860 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2338. Min Act: -0.1700
Data Index: 4080673 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2650. Min Act: -0.1700
Data Index: 1524714 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2338. Min Act: -0.1700
Data Index: 4028235 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2650. Min Act: -0.1700
Data Index: 3823977 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2650. Min Act: -0.1700
Data Index: 123606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2338. Min Act: -0.1700
Data Index: 3736092 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3588. Min Range: -4.3588
Max Act: 4.2650. Min Act: -0.1700
Data Index: 1333035 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19