Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1547 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0693. Min Range: -6.0693
Max Act: 6.0693. Min Act: -0.1700
Data Index: 221140 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0693. Min Range: -6.0693
Max Act: 6.0068. Min Act: -0.1700
Data Index: 3391148 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.9130. Min Act: -0.1700
Data Index: 1618125 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.8818. Min Act: -0.1700
Data Index: 4198889 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.8505. Min Act: -0.1700
Data Index: 4727067 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.8505. Min Act: -0.1700
Data Index: 302180 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.8505. Min Act: -0.1700
Data Index: 271169 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.8193. Min Act: -0.1700
Data Index: 4600896 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.8505. Min Act: -0.1700
Data Index: 6583434 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.7880. Min Act: -0.1700
Data Index: 5351614 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.7568. Min Act: -0.1700
Data Index: 6067173 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.7880. Min Act: -0.1700
Data Index: 3111280 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.7568. Min Act: -0.1700
Data Index: 6646330 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.7255. Min Act: -0.1700
Data Index: 254485 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.7568. Min Act: -0.1700
Data Index: 804093 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.7880. Min Act: -0.1700
Data Index: 7973385 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.7880. Min Act: -0.1700
Data Index: 2747461 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.6943. Min Act: -0.1700
Data Index: 2857136 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.7255. Min Act: -0.1700
Data Index: 264353 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0693. Min Range: -6.0693
Max Act: 5.7568. Min Act: -0.1700
Data Index: 4220771 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19