Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.4284. Min Act: -0.1700
Data Index: 191070 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.3659. Min Act: -0.1700
Data Index: 1517609 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.3347. Min Act: -0.1700
Data Index: 6785148 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.3034. Min Act: -0.1700
Data Index: 6591628 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.2097. Min Act: -0.1700
Data Index: 5084652 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.2097. Min Act: -0.1700
Data Index: 1903900 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.1784. Min Act: -0.1700
Data Index: 7192980 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.1159. Min Act: -0.1700
Data Index: 2270326 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.1159. Min Act: -0.1700
Data Index: 3081375 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.0847. Min Act: -0.1700
Data Index: 4173544 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.0847. Min Act: -0.1700
Data Index: 1419608 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4284. Min Range: -5.4284
Max Act: 5.0534. Min Act: -0.1700
Data Index: 8353220 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4284. Min Range: -5.4284
Max Act: 4.9909. Min Act: -0.1700
Data Index: 2292344 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4284. Min Range: -5.4284
Max Act: 4.9597. Min Act: -0.1700
Data Index: 5407233 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4284. Min Range: -5.4284
Max Act: 4.9597. Min Act: -0.1700
Data Index: 5415096 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4284. Min Range: -5.4284
Max Act: 4.9284. Min Act: -0.1700
Data Index: 7755103 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4284. Min Range: -5.4284
Max Act: 4.9284. Min Act: -0.1700
Data Index: 2686246 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4284. Min Range: -5.4284
Max Act: 4.9597. Min Act: -0.1700
Data Index: 3639059 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4284. Min Range: -5.4284
Max Act: 4.9284. Min Act: -0.1700
Data Index: 5491436 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4284. Min Range: -5.4284
Max Act: 4.8972. Min Act: -0.1700
Data Index: 3391261 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19