Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4748 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1816. Min Range: -6.1816
Max Act: 6.1816. Min Act: -0.1700
Data Index: 2841466 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1816. Min Range: -6.1816
Max Act: 6.0566. Min Act: -0.1700
Data Index: 3829414 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1816. Min Range: -6.1816
Max Act: 6.0566. Min Act: -0.1700
Data Index: 7914023 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.9316. Min Act: -0.1700
Data Index: 2126896 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.9003. Min Act: -0.1700
Data Index: 877286 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.9003. Min Act: -0.1700
Data Index: 8029786 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.9003. Min Act: -0.1700
Data Index: 920910 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.8691. Min Act: -0.1700
Data Index: 7364999 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.8691. Min Act: -0.1700
Data Index: 8117264 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.8378. Min Act: -0.1700
Data Index: 82961 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.8378. Min Act: -0.1700
Data Index: 1570135 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.7441. Min Act: -0.1700
Data Index: 536040 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.7753. Min Act: -0.1700
Data Index: 84289 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.7441. Min Act: -0.1700
Data Index: 6056625 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.7441. Min Act: -0.1699
Data Index: 8699457 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.7441. Min Act: -0.1700
Data Index: 7860797 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.7441. Min Act: -0.1700
Data Index: 4233967 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.7441. Min Act: -0.1700
Data Index: 2509620 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.7128. Min Act: -0.1700
Data Index: 2490012 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1816. Min Range: -6.1816
Max Act: 5.6816. Min Act: -0.1700
Data Index: 4135191 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19