Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1162 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.6019. Min Act: -0.1700
Data Index: 4328021 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.4144. Min Act: -0.1700
Data Index: 1819028 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.4457. Min Act: -0.1700
Data Index: 2199065 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.3832. Min Act: -0.1700
Data Index: 163159 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.3519. Min Act: -0.1700
Data Index: 1341994 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.3519. Min Act: -0.1700
Data Index: 7720095 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.3832. Min Act: -0.1700
Data Index: 6787126 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.3519. Min Act: -0.1700
Data Index: 456694 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.3519. Min Act: -0.1700
Data Index: 456531 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.3207. Min Act: -0.1700
Data Index: 3582023 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.2894. Min Act: -0.1700
Data Index: 1643472 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.2894. Min Act: -0.1700
Data Index: 6101421 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.2894. Min Act: -0.1700
Data Index: 5389434 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.2894. Min Act: -0.1700
Data Index: 6312017 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.2894. Min Act: -0.1700
Data Index: 7927684 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.2894. Min Act: -0.1700
Data Index: 5724976 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.2894. Min Act: -0.1700
Data Index: 4598921 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.2894. Min Act: -0.1700
Data Index: 6028093 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.2582. Min Act: -0.1700
Data Index: 3840607 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6019. Min Range: -4.6019
Max Act: 4.2582. Min Act: -0.1700
Data Index: 7106864 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19