Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3133 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.2782. Min Act: -0.1700
Data Index: 2283378 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.2468. Min Act: -0.1700
Data Index: 7515086 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.1682. Min Act: -0.1700
Data Index: 1118479 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.1525. Min Act: -0.1700
Data Index: 765902 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.1367. Min Act: -0.1700
Data Index: 2384273 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.0421. Min Act: -0.1700
Data Index: 7642914 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.0579. Min Act: -0.1700
Data Index: 7773291 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.0421. Min Act: -0.1700
Data Index: 2481359 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.0579. Min Act: -0.1700
Data Index: 4727636 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.0105. Min Act: -0.1700
Data Index: 387674 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.0263. Min Act: -0.1700
Data Index: 280315 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.0421. Min Act: -0.1700
Data Index: 7634240 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.0105. Min Act: -0.1700
Data Index: 713285 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2782. Min Range: -3.2782
Max Act: 2.9789. Min Act: -0.1700
Data Index: 8744831 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2782. Min Range: -3.2782
Max Act: 3.0105. Min Act: -0.1700
Data Index: 4433856 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2782. Min Range: -3.2782
Max Act: 2.9947. Min Act: -0.1700
Data Index: 4589209 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2782. Min Range: -3.2782
Max Act: 2.9947. Min Act: -0.1700
Data Index: 5931470 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2782. Min Range: -3.2782
Max Act: 2.9947. Min Act: -0.1700
Data Index: 8451598 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2782. Min Range: -3.2782
Max Act: 2.9789. Min Act: -0.1700
Data Index: 7119409 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2782. Min Range: -3.2782
Max Act: 2.9631. Min Act: -0.1700
Data Index: 405363 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19