Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.9151. Min Act: -0.1700
Data Index: 590448 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.9151. Min Act: -0.1700
Data Index: 6188109 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.7901. Min Act: -0.1700
Data Index: 5342488 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.7276. Min Act: -0.1700
Data Index: 295212 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.6339. Min Act: -0.1700
Data Index: 312074 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.6651. Min Act: -0.1700
Data Index: 2535790 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.6651. Min Act: -0.1700
Data Index: 6606047 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.6964. Min Act: -0.1700
Data Index: 1757160 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.6339. Min Act: -0.1700
Data Index: 3136489 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.6026. Min Act: -0.1700
Data Index: 4918763 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.5714. Min Act: -0.1700
Data Index: 4868662 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.6026. Min Act: -0.1700
Data Index: 3578080 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.5401. Min Act: -0.1700
Data Index: 6594527 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.5714. Min Act: -0.1700
Data Index: 2789752 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.5401. Min Act: -0.1700
Data Index: 6844925 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.5089. Min Act: -0.1700
Data Index: 8049819 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.5401. Min Act: -0.1700
Data Index: 1496664 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.5089. Min Act: -0.1700
Data Index: 3721867 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.5089. Min Act: -0.1700
Data Index: 1496662 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9151. Min Range: -5.9151
Max Act: 5.4776. Min Act: -0.1700
Data Index: 4950231 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19