Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1157 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.5594. Min Act: -0.1700
Data Index: 7877579 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.5419. Min Act: -0.1700
Data Index: 7877578 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.5331. Min Act: -0.1700
Data Index: 439486 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.5156. Min Act: -0.1700
Data Index: 3378090 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.5331. Min Act: -0.1700
Data Index: 313092 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.5156. Min Act: -0.1700
Data Index: 2473427 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.5156. Min Act: -0.1700
Data Index: 7089627 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.5068. Min Act: -0.1700
Data Index: 2501664 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4981. Min Act: -0.1700
Data Index: 2087025 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.5068. Min Act: -0.1700
Data Index: 6099008 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4893. Min Act: -0.1700
Data Index: 2363721 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4893. Min Act: -0.1687
Data Index: 1097740 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4717. Min Act: -0.1700
Data Index: 6916142 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4893. Min Act: -0.1698
Data Index: 4396412 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4805. Min Act: -0.1700
Data Index: 4108096 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4717. Min Act: -0.1699
Data Index: 5546138 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4893. Min Act: -0.1700
Data Index: 5011892 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4805. Min Act: -0.1700
Data Index: 7480321 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4805. Min Act: -0.1700
Data Index: 3557253 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5594. Min Range: -1.5594
Max Act: 1.4717. Min Act: -0.1700
Data Index: 3424360 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19