Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0388. Min Range: -2.0388
Max Act: 2.0388. Min Act: -0.1700
Data Index: 4652252 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.9203. Min Act: -0.1700
Data Index: 5045645 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.8435. Min Act: -0.1700
Data Index: 4908880 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.8520. Min Act: -0.1700
Data Index: 6369137 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.8177. Min Act: -0.1693
Data Index: 78397 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.8177. Min Act: -0.1700
Data Index: 5601229 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.8005. Min Act: -0.1699
Data Index: 5950119 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7833. Min Act: -0.1700
Data Index: 8453219 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7919. Min Act: -0.1696
Data Index: 929418 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.8005. Min Act: -0.1700
Data Index: 4298312 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7833. Min Act: -0.1700
Data Index: 8387364 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7833. Min Act: -0.1700
Data Index: 5269160 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7833. Min Act: -0.1700
Data Index: 4250941 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7661. Min Act: -0.1700
Data Index: 2170604 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7574. Min Act: -0.1700
Data Index: 8779781 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7574. Min Act: -0.1700
Data Index: 3695656 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7574. Min Act: -0.1700
Data Index: 816625 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7574. Min Act: -0.1699
Data Index: 8319212 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7488. Min Act: -0.1699
Data Index: 3053291 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0388. Min Range: -2.0388
Max Act: 1.7402. Min Act: -0.1700
Data Index: 1299100 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19