Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6385 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.4475. Min Act: -0.1700
Data Index: 8552210 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.3537. Min Act: -0.1700
Data Index: 2734519 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.3537. Min Act: -0.1700
Data Index: 932598 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.3537. Min Act: -0.1700
Data Index: 3663704 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.3225. Min Act: -0.1700
Data Index: 4432950 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.3225. Min Act: -0.1700
Data Index: 1252925 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.3225. Min Act: -0.1700
Data Index: 4163521 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2600. Min Act: -0.1700
Data Index: 7092298 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2600. Min Act: -0.1700
Data Index: 4038846 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2287. Min Act: -0.1700
Data Index: 4057204 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2287. Min Act: -0.1700
Data Index: 1793707 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2287. Min Act: -0.1700
Data Index: 676326 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2287. Min Act: -0.1700
Data Index: 1494527 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2287. Min Act: -0.1700
Data Index: 606895 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2287. Min Act: -0.1700
Data Index: 4718251 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2287. Min Act: -0.1700
Data Index: 5677286 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.1975. Min Act: -0.1700
Data Index: 6557873 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2287. Min Act: -0.1700
Data Index: 149174 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2287. Min Act: -0.1700
Data Index: 7466274 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4475. Min Range: -5.4475
Max Act: 5.2287. Min Act: -0.1700
Data Index: 19715 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19