Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2902 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0860. Min Range: -5.0860
Max Act: 5.0860. Min Act: -0.1700
Data Index: 2411192 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0860. Min Range: -5.0860
Max Act: 5.0860. Min Act: -0.1700
Data Index: 5532054 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0860. Min Range: -5.0860
Max Act: 5.0235. Min Act: -0.1700
Data Index: 5583021 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0860. Min Range: -5.0860
Max Act: 5.0235. Min Act: -0.1700
Data Index: 2579228 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.9610. Min Act: -0.1700
Data Index: 5640772 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8673. Min Act: -0.1700
Data Index: 1610293 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8360. Min Act: -0.1700
Data Index: 1881998 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8673. Min Act: -0.1700
Data Index: 1497996 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8673. Min Act: -0.1700
Data Index: 4083913 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8360. Min Act: -0.1700
Data Index: 4305308 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8360. Min Act: -0.1700
Data Index: 220002 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8360. Min Act: -0.1700
Data Index: 300443 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8360. Min Act: -0.1700
Data Index: 451370 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8048. Min Act: -0.1700
Data Index: 7572401 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8048. Min Act: -0.1700
Data Index: 6267070 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.8048. Min Act: -0.1700
Data Index: 7798276 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.7735. Min Act: -0.1700
Data Index: 8335541 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.7735. Min Act: -0.1700
Data Index: 5357121 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.7423. Min Act: -0.1700
Data Index: 4591376 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0860. Min Range: -5.0860
Max Act: 4.7423. Min Act: -0.1700
Data Index: 31262 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19