Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7678. Min Act: -0.1700
Data Index: 4146497 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7991. Min Act: -0.1700
Data Index: 4161543 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7991. Min Act: -0.1700
Data Index: 4663200 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7053. Min Act: -0.1700
Data Index: 2498157 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7366. Min Act: -0.1700
Data Index: 4978442 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7053. Min Act: -0.1700
Data Index: 6161580 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7053. Min Act: -0.1700
Data Index: 761048 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7053. Min Act: -0.1700
Data Index: 4854408 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6740. Min Act: -0.1700
Data Index: 5211570 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6740. Min Act: -0.1700
Data Index: 2955058 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6740. Min Act: -0.1700
Data Index: 7145571 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6427. Min Act: -0.1700
Data Index: 4234034 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6427. Min Act: -0.1700
Data Index: 2874774 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6114. Min Act: -0.1700
Data Index: 2573172 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6427. Min Act: -0.1700
Data Index: 5185771 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6427. Min Act: -0.1700
Data Index: 6678671 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6740. Min Act: -0.1700
Data Index: 1053107 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6427. Min Act: -0.1700
Data Index: 6726823 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6114. Min Act: -0.1700
Data Index: 4643886 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6427. Min Act: -0.1700
Data Index: 8155357 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19