Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2327 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.7423. Min Act: -0.1700
Data Index: 2148600 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.7111. Min Act: -0.1700
Data Index: 4908773 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.7111. Min Act: -0.1700
Data Index: 3656373 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.7111. Min Act: -0.1700
Data Index: 2096735 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6798. Min Act: -0.1700
Data Index: 4908777 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6798. Min Act: -0.1700
Data Index: 1595624 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6486. Min Act: -0.1700
Data Index: 226753 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6798. Min Act: -0.1700
Data Index: 8258596 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6486. Min Act: -0.1700
Data Index: 306600 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6486. Min Act: -0.1700
Data Index: 2737723 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6173. Min Act: -0.1700
Data Index: 4495633 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6486. Min Act: -0.1700
Data Index: 7664956 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6173. Min Act: -0.1700
Data Index: 7781834 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5861. Min Act: -0.1700
Data Index: 4104024 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.6173. Min Act: -0.1700
Data Index: 5287925 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5861. Min Act: -0.1700
Data Index: 4269523 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5548. Min Act: -0.1700
Data Index: 382166 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5236. Min Act: -0.1700
Data Index: 4908774 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5548. Min Act: -0.1700
Data Index: 5164644 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7423. Min Range: -4.7423
Max Act: 4.5861. Min Act: -0.1700
Data Index: 6067949 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19