Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4093 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.5613. Min Act: -0.1700
Data Index: 588801 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.5438. Min Act: -0.1700
Data Index: 409004 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.5175. Min Act: -0.1699
Data Index: 6005796 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.5175. Min Act: -0.1693
Data Index: 1737236 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.5175. Min Act: -0.1700
Data Index: 5380617 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.5087. Min Act: -0.1690
Data Index: 7696263 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4912. Min Act: -0.1700
Data Index: 8580098 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.5000. Min Act: -0.1700
Data Index: 1739265 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4824. Min Act: -0.1700
Data Index: 1415329 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4912. Min Act: -0.1700
Data Index: 6389122 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4912. Min Act: -0.1694
Data Index: 3305887 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4736. Min Act: -0.1700
Data Index: 7865871 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4736. Min Act: -0.1700
Data Index: 8773922 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4736. Min Act: -0.1700
Data Index: 900278 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4736. Min Act: -0.1700
Data Index: 199502 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4560. Min Act: -0.1700
Data Index: 8166182 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4560. Min Act: -0.1700
Data Index: 5235759 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4648. Min Act: -0.1698
Data Index: 596625 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4648. Min Act: -0.1700
Data Index: 6036169 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5613. Min Range: -1.5613
Max Act: 1.4472. Min Act: -0.1700
Data Index: 4982427 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19