Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3939. Min Range: -9.3939
Max Act: 9.3939. Min Act: -0.1700
Data Index: 7232621 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3939. Min Range: -9.3939
Max Act: 9.3314. Min Act: -0.1700
Data Index: 8092011 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3939. Min Range: -9.3939
Max Act: 9.3314. Min Act: -0.1700
Data Index: 2145233 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3939. Min Range: -9.3939
Max Act: 9.2689. Min Act: -0.1700
Data Index: 2704194 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3939. Min Range: -9.3939
Max Act: 9.2064. Min Act: -0.1700
Data Index: 1384174 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3939. Min Range: -9.3939
Max Act: 9.0814. Min Act: -0.1700
Data Index: 342506 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3939. Min Range: -9.3939
Max Act: 9.0814. Min Act: -0.1700
Data Index: 7843082 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3939. Min Range: -9.3939
Max Act: 9.0814. Min Act: -0.1700
Data Index: 2562803 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.9564. Min Act: -0.1700
Data Index: 2908727 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.9564. Min Act: -0.1700
Data Index: 6509679 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.9564. Min Act: -0.1700
Data Index: 6296986 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.8939. Min Act: -0.1700
Data Index: 6680589 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.8939. Min Act: -0.1700
Data Index: 302132 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.8939. Min Act: -0.1700
Data Index: 7415997 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.8939. Min Act: -0.1700
Data Index: 4057891 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.8939. Min Act: -0.1700
Data Index: 6523565 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.8314. Min Act: -0.1700
Data Index: 6463327 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.8939. Min Act: -0.1700
Data Index: 3249119 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.8314. Min Act: -0.1700
Data Index: 1093186 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3939. Min Range: -9.3939
Max Act: 8.7689. Min Act: -0.1700
Data Index: 6934697 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19