Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.5444. Min Act: -0.1700
Data Index: 8831223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.5120. Min Act: -0.1700
Data Index: 4418824 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.4796. Min Act: -0.1700
Data Index: 5851463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.4796. Min Act: -0.1700
Data Index: 1851883 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.4958. Min Act: -0.1700
Data Index: 60567 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.4796. Min Act: -0.1700
Data Index: 6369905 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.4471. Min Act: -0.1700
Data Index: 4607512 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.4471. Min Act: -0.1700
Data Index: 5069435 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.4471. Min Act: -0.1700
Data Index: 6784492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.4471. Min Act: -0.1700
Data Index: 3054414 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.3983. Min Act: -0.1700
Data Index: 4580562 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.3819. Min Act: -0.1700
Data Index: 7805200 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.3819. Min Act: -0.1700
Data Index: 8698160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.3656. Min Act: -0.1700
Data Index: 2663165 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.3492. Min Act: -0.1700
Data Index: 7916989 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.3492. Min Act: -0.1700
Data Index: 4325933 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.3328. Min Act: -0.1700
Data Index: 65167 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.3328. Min Act: -0.1700
Data Index: 2740262 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.3492. Min Act: -0.1700
Data Index: 6523558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5444. Min Range: -2.5444
Max Act: 2.3328. Min Act: -0.1700
Data Index: 2591950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19