Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2718 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.3618. Min Act: -0.1700
Data Index: 5289798 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.3618. Min Act: -0.1700
Data Index: 3636382 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.3290. Min Act: -0.1700
Data Index: 5099825 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.3290. Min Act: -0.1700
Data Index: 1618206 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.3454. Min Act: -0.1700
Data Index: 7056310 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.3126. Min Act: -0.1700
Data Index: 8097808 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.3126. Min Act: -0.1700
Data Index: 8336401 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.3126. Min Act: -0.1700
Data Index: 899293 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2797. Min Act: -0.1700
Data Index: 2452596 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2797. Min Act: -0.1700
Data Index: 7371318 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2467. Min Act: -0.1700
Data Index: 7740167 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2467. Min Act: -0.1700
Data Index: 1821902 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2301. Min Act: -0.1700
Data Index: 8433936 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2467. Min Act: -0.1700
Data Index: 384035 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2467. Min Act: -0.1700
Data Index: 3648023 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2467. Min Act: -0.1700
Data Index: 7650580 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2301. Min Act: -0.1700
Data Index: 2959663 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2301. Min Act: -0.1700
Data Index: 2898137 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2301. Min Act: -0.1700
Data Index: 4870790 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3618. Min Range: -2.3618
Max Act: 2.2301. Min Act: -0.1700
Data Index: 3914970 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19