Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2684 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.2933. Min Act: -0.1700
Data Index: 7667768 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.2620. Min Act: -0.1700
Data Index: 6649374 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.2620. Min Act: -0.1700
Data Index: 2668619 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.2620. Min Act: -0.1700
Data Index: 3113057 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.2308. Min Act: -0.1700
Data Index: 1404163 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.2308. Min Act: -0.1700
Data Index: 8065381 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1995. Min Act: -0.1700
Data Index: 603989 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1995. Min Act: -0.1700
Data Index: 823867 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1995. Min Act: -0.1700
Data Index: 6326640 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1995. Min Act: -0.1700
Data Index: 8773329 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1683. Min Act: -0.1700
Data Index: 5878167 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.2308. Min Act: -0.1700
Data Index: 2684227 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1683. Min Act: -0.1700
Data Index: 3750295 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1370. Min Act: -0.1700
Data Index: 2737789 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1683. Min Act: -0.1700
Data Index: 2176190 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1683. Min Act: -0.1700
Data Index: 1664641 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1683. Min Act: -0.1700
Data Index: 841819 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1683. Min Act: -0.1700
Data Index: 5763647 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1683. Min Act: -0.1700
Data Index: 7058044 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2933. Min Range: -5.2933
Max Act: 5.1370. Min Act: -0.1700
Data Index: 3316121 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19