Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4094 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.5646. Min Act: -0.1700
Data Index: 4650680 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.5334. Min Act: -0.1700
Data Index: 1864382 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.5334. Min Act: -0.1700
Data Index: 4060830 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.4709. Min Act: -0.1700
Data Index: 1897375 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.4396. Min Act: -0.1700
Data Index: 4795920 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.4396. Min Act: -0.1700
Data Index: 4338899 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.3771. Min Act: -0.1700
Data Index: 1253022 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.3459. Min Act: -0.1700
Data Index: 6355127 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.3459. Min Act: -0.1700
Data Index: 1031648 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.2834. Min Act: -0.1700
Data Index: 8305412 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.3146. Min Act: -0.1700
Data Index: 4000303 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.2834. Min Act: -0.1700
Data Index: 6782280 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.2834. Min Act: -0.1700
Data Index: 5970763 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.2834. Min Act: -0.1700
Data Index: 5773159 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.2521. Min Act: -0.1700
Data Index: 3751871 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.2209. Min Act: -0.1700
Data Index: 7649025 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.2521. Min Act: -0.1700
Data Index: 232711 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.2521. Min Act: -0.1700
Data Index: 8255786 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.2209. Min Act: -0.1700
Data Index: 2772771 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5646. Min Range: -5.5646
Max Act: 5.2209. Min Act: -0.1700
Data Index: 2626522 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19