Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.9215. Min Act: -0.1700
Data Index: 4393038 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.9215. Min Act: -0.1700
Data Index: 5699961 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.9056. Min Act: -0.1700
Data Index: 1924794 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.8421. Min Act: -0.1700
Data Index: 2476316 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.8103. Min Act: -0.1700
Data Index: 1576108 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.7944. Min Act: -0.1700
Data Index: 1811537 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.7944. Min Act: -0.1700
Data Index: 8208725 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.7625. Min Act: -0.1700
Data Index: 2011936 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.7466. Min Act: -0.1700
Data Index: 237540 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.7306. Min Act: -0.1700
Data Index: 5157845 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.7306. Min Act: -0.1700
Data Index: 3073063 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.7306. Min Act: -0.1700
Data Index: 5818580 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.7146. Min Act: -0.1700
Data Index: 3551103 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.7146. Min Act: -0.1700
Data Index: 110314 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.7146. Min Act: -0.1700
Data Index: 3663959 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.6826. Min Act: -0.1700
Data Index: 211514 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.6826. Min Act: -0.1700
Data Index: 3343756 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.6826. Min Act: -0.1700
Data Index: 3450256 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.6666. Min Act: -0.1700
Data Index: 579689 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9215. Min Range: -2.9215
Max Act: 2.6826. Min Act: -0.1700
Data Index: 7131373 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19