Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2888 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.4521. Min Act: -0.1700
Data Index: 3095045 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.3896. Min Act: -0.1700
Data Index: 3412640 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.3896. Min Act: -0.1700
Data Index: 560979 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.4208. Min Act: -0.1700
Data Index: 1512565 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2958. Min Act: -0.1700
Data Index: 7825462 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2958. Min Act: -0.1700
Data Index: 3618907 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2958. Min Act: -0.1700
Data Index: 4987557 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2646. Min Act: -0.1700
Data Index: 2024486 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2333. Min Act: -0.1700
Data Index: 3678966 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2646. Min Act: -0.1700
Data Index: 7014520 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2021. Min Act: -0.1700
Data Index: 5371423 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2333. Min Act: -0.1700
Data Index: 644896 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2021. Min Act: -0.1700
Data Index: 7713489 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2333. Min Act: -0.1700
Data Index: 1664291 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2021. Min Act: -0.1700
Data Index: 1966422 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2021. Min Act: -0.1700
Data Index: 696549 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.1396. Min Act: -0.1700
Data Index: 1059528 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.1083. Min Act: -0.1700
Data Index: 953189 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.1083. Min Act: -0.1700
Data Index: 8306734 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.1083. Min Act: -0.1700
Data Index: 8368371 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19