Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3695 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.1682. Min Act: -0.1700
Data Index: 8244075 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.1516. Min Act: -0.1700
Data Index: 3632727 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.1516. Min Act: -0.1700
Data Index: 5590011 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.1014. Min Act: -0.1700
Data Index: 5970754 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.1014. Min Act: -0.1700
Data Index: 5760531 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.1014. Min Act: -0.1700
Data Index: 1708850 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.0511. Min Act: -0.1700
Data Index: 4807846 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.0343. Min Act: -0.1700
Data Index: 1530314 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.0343. Min Act: -0.1700
Data Index: 5970748 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.0174. Min Act: -0.1700
Data Index: 7435985 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.0174. Min Act: -0.1700
Data Index: 4037064 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.0174. Min Act: -0.1700
Data Index: 2271836 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.0005. Min Act: -0.1700
Data Index: 4519407 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1682. Min Range: -2.1682
Max Act: 1.9836. Min Act: -0.1700
Data Index: 2299013 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.0005. Min Act: -0.1700
Data Index: 4060734 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1682. Min Range: -2.1682
Max Act: 2.0005. Min Act: -0.1700
Data Index: 2857824 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1682. Min Range: -2.1682
Max Act: 1.9836. Min Act: -0.1699
Data Index: 1547248 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1682. Min Range: -2.1682
Max Act: 1.9667. Min Act: -0.1700
Data Index: 3635651 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1682. Min Range: -2.1682
Max Act: 1.9836. Min Act: -0.1700
Data Index: 3231520 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1682. Min Range: -2.1682
Max Act: 1.9667. Min Act: -0.1700
Data Index: 3820830 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19