Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1962. Min Act: -0.1700
Data Index: 8236645 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1962. Min Act: -0.1700
Data Index: 3076276 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1649. Min Act: -0.1700
Data Index: 2174019 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1962. Min Act: -0.1700
Data Index: 1977276 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1962. Min Act: -0.1700
Data Index: 2343611 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1962. Min Act: -0.1700
Data Index: 4034490 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1649. Min Act: -0.1700
Data Index: 2373969 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1024. Min Act: -0.1700
Data Index: 2740740 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1337. Min Act: -0.1700
Data Index: 7751972 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1337. Min Act: -0.1700
Data Index: 986021 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1024. Min Act: -0.1700
Data Index: 530830 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.0711. Min Act: -0.1700
Data Index: 6038935 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.0711. Min Act: -0.1700
Data Index: 24167 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.1024. Min Act: -0.1700
Data Index: 5595990 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.0711. Min Act: -0.1700
Data Index: 5301192 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.0711. Min Act: -0.1700
Data Index: 1030862 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.0399. Min Act: -0.1700
Data Index: 3320253 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.0711. Min Act: -0.1700
Data Index: 5296515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.0711. Min Act: -0.1700
Data Index: 4803678 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1962. Min Range: -4.1962
Max Act: 4.0711. Min Act: -0.1700
Data Index: 3022376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19