Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.4051. Min Act: -0.1700
Data Index: 2561774 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.4377. Min Act: -0.1700
Data Index: 1636461 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.4051. Min Act: -0.1700
Data Index: 978856 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.1412. Min Act: -0.1700
Data Index: 2293589 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2903. Min Act: -0.1700
Data Index: 6738658 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2574. Min Act: -0.1700
Data Index: 6763748 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2408. Min Act: -0.1700
Data Index: 6429177 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.1745. Min Act: -0.1700
Data Index: 3046250 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2739. Min Act: -0.1700
Data Index: 4494524 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2077. Min Act: -0.1700
Data Index: 6463860 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2077. Min Act: -0.1700
Data Index: 5336318 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2408. Min Act: -0.1700
Data Index: 5735835 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2243. Min Act: -0.1700
Data Index: 8389600 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2077. Min Act: -0.1700
Data Index: 7065335 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2243. Min Act: -0.1700
Data Index: 688195 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.2739. Min Act: -0.1700
Data Index: 7780144 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.1412. Min Act: -0.1700
Data Index: 3941063 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.1412. Min Act: -0.1700
Data Index: 2221542 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.1911. Min Act: -0.1700
Data Index: 7608722 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4377. Min Range: -2.4377
Max Act: 2.1911. Min Act: -0.1700
Data Index: 5504128 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19