Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 84 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.1855. Min Act: -0.1700
Data Index: 2789839 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.1230. Min Act: -0.1700
Data Index: 8225249 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.1230. Min Act: -0.1700
Data Index: 7193819 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.0917. Min Act: -0.1700
Data Index: 8775016 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.0605. Min Act: -0.1700
Data Index: 4885432 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.0605. Min Act: -0.1700
Data Index: 1386293 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.0292. Min Act: -0.1700
Data Index: 8184037 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.0292. Min Act: -0.1700
Data Index: 4169531 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.0292. Min Act: -0.1700
Data Index: 1515465 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.0292. Min Act: -0.1700
Data Index: 1358243 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1855. Min Range: -5.1855
Max Act: 4.9980. Min Act: -0.1700
Data Index: 7580268 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1855. Min Range: -5.1855
Max Act: 4.9980. Min Act: -0.1700
Data Index: 4075768 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1855. Min Range: -5.1855
Max Act: 5.0292. Min Act: -0.1700
Data Index: 2146800 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1855. Min Range: -5.1855
Max Act: 4.9667. Min Act: -0.1700
Data Index: 4636164 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1855. Min Range: -5.1855
Max Act: 4.9980. Min Act: -0.1700
Data Index: 71913 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1855. Min Range: -5.1855
Max Act: 4.9980. Min Act: -0.1700
Data Index: 1212169 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1855. Min Range: -5.1855
Max Act: 4.9667. Min Act: -0.1700
Data Index: 7172961 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1855. Min Range: -5.1855
Max Act: 4.9980. Min Act: -0.1700
Data Index: 4345920 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1855. Min Range: -5.1855
Max Act: 4.9980. Min Act: -0.1700
Data Index: 5622399 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1855. Min Range: -5.1855
Max Act: 4.9980. Min Act: -0.1700
Data Index: 5537704 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19