Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6385 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2339. Min Range: -11.2339
Max Act: 11.2339. Min Act: -0.1700
Data Index: 7842089 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2339. Min Range: -11.2339
Max Act: 11.0464. Min Act: -0.1700
Data Index: 2176408 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2339. Min Range: -11.2339
Max Act: 11.0464. Min Act: -0.1700
Data Index: 1936120 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2339. Min Range: -11.2339
Max Act: 11.0464. Min Act: -0.1700
Data Index: 8175092 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2339. Min Range: -11.2339
Max Act: 11.0464. Min Act: -0.1700
Data Index: 162057 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.9839. Min Act: -0.1690
Data Index: 4598755 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.9839. Min Act: -0.1700
Data Index: 6183299 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.9839. Min Act: -0.1700
Data Index: 211538 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.9839. Min Act: -0.1700
Data Index: 7655604 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.9214. Min Act: -0.1700
Data Index: 63571 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.9214. Min Act: -0.1700
Data Index: 4651842 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.9214. Min Act: -0.1699
Data Index: 672789 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.8589. Min Act: -0.1700
Data Index: 2831806 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.8589. Min Act: -0.1699
Data Index: 2720566 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.8589. Min Act: -0.1700
Data Index: 211530 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.8589. Min Act: -0.1700
Data Index: 6046307 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.8589. Min Act: -0.1700
Data Index: 6595014 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.8589. Min Act: -0.1700
Data Index: 4764216 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.7964. Min Act: -0.1687
Data Index: 2359016 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2339. Min Range: -11.2339
Max Act: 10.7964. Min Act: -0.1699
Data Index: 1744493 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19