Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3684 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.9674. Min Act: -0.1700
Data Index: 5257080 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.9674. Min Act: -0.1700
Data Index: 1286377 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.9362. Min Act: -0.1700
Data Index: 2401925 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.9362. Min Act: -0.1700
Data Index: 2209887 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8737. Min Act: -0.1700
Data Index: 998473 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8737. Min Act: -0.1700
Data Index: 2082465 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8424. Min Act: -0.1700
Data Index: 2051114 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8424. Min Act: -0.1700
Data Index: 2350129 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8737. Min Act: -0.1700
Data Index: 7146655 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8737. Min Act: -0.1700
Data Index: 3676554 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8112. Min Act: -0.1700
Data Index: 2195053 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8424. Min Act: -0.1700
Data Index: 195687 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8424. Min Act: -0.1700
Data Index: 6714312 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8424. Min Act: -0.1700
Data Index: 6511627 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 4714871 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 1831 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 7118157 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 4616511 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.8112. Min Act: -0.1700
Data Index: 3609377 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9674. Min Range: -4.9674
Max Act: 4.7799. Min Act: -0.1700
Data Index: 4743396 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19