Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 930 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.3637. Min Act: -0.1700
Data Index: 2658485 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1762. Min Act: -0.1700
Data Index: 5145710 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.1137. Min Act: -0.1700
Data Index: 6514456 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0512. Min Act: -0.1700
Data Index: 6558091 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0512. Min Act: -0.1700
Data Index: 4616246 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0512. Min Act: -0.1700
Data Index: 4369956 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0199. Min Act: -0.1700
Data Index: 6443531 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0199. Min Act: -0.1700
Data Index: 6709811 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9887. Min Act: -0.1700
Data Index: 4668878 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3637. Min Range: -5.3637
Max Act: 5.0199. Min Act: -0.1700
Data Index: 8809626 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9574. Min Act: -0.1700
Data Index: 1042971 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9887. Min Act: -0.1700
Data Index: 7665294 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9574. Min Act: -0.1700
Data Index: 3726387 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9574. Min Act: -0.1700
Data Index: 3892119 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9574. Min Act: -0.1700
Data Index: 7649402 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9887. Min Act: -0.1700
Data Index: 4133379 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9574. Min Act: -0.1700
Data Index: 1098356 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9574. Min Act: -0.1700
Data Index: 7649401 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9887. Min Act: -0.1700
Data Index: 7453612 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3637. Min Range: -5.3637
Max Act: 4.9574. Min Act: -0.1700
Data Index: 4373890 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19