Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.9864. Min Act: -0.1700
Data Index: 6160486 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.9239. Min Act: -0.1700
Data Index: 1934658 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7989. Min Act: -0.1700
Data Index: 937087 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.8302. Min Act: -0.1700
Data Index: 5604054 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7989. Min Act: -0.1700
Data Index: 5185271 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7677. Min Act: -0.1700
Data Index: 4247073 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7677. Min Act: -0.1700
Data Index: 5604056 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7677. Min Act: -0.1696
Data Index: 5185274 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7677. Min Act: -0.1700
Data Index: 5604055 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7989. Min Act: -0.1700
Data Index: 4247077 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7364. Min Act: -0.1700
Data Index: 22324 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7364. Min Act: -0.1700
Data Index: 5020310 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7364. Min Act: -0.1700
Data Index: 4247075 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7364. Min Act: -0.1700
Data Index: 4247074 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7364. Min Act: -0.1700
Data Index: 3251470 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7052. Min Act: -0.1700
Data Index: 8557005 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.6739. Min Act: -0.1700
Data Index: 3251467 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.6739. Min Act: -0.1700
Data Index: 838727 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.6739. Min Act: -0.1700
Data Index: 5185269 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.6427. Min Act: -0.1700
Data Index: 1126072 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19