Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1226. Min Range: -7.1226
Max Act: 7.1226. Min Act: -0.1700
Data Index: 1009755 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1226. Min Range: -7.1226
Max Act: 7.0601. Min Act: -0.1700
Data Index: 3124545 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.9351. Min Act: -0.1700
Data Index: 7650058 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.9039. Min Act: -0.1700
Data Index: 1459288 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.9351. Min Act: -0.1700
Data Index: 503222 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.8726. Min Act: -0.1700
Data Index: 6012020 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.8726. Min Act: -0.1700
Data Index: 2410579 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.8414. Min Act: -0.1700
Data Index: 1586789 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.7476. Min Act: -0.1700
Data Index: 3967591 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.7476. Min Act: -0.1700
Data Index: 7504461 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.6539. Min Act: -0.1700
Data Index: 963355 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.6539. Min Act: -0.1700
Data Index: 8086930 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.6851. Min Act: -0.1700
Data Index: 8598412 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.6226. Min Act: -0.1700
Data Index: 2181992 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.5914. Min Act: -0.1700
Data Index: 5016919 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 3513141 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 4885034 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 26627 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.5601. Min Act: -0.1700
Data Index: 4465227 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1226. Min Range: -7.1226
Max Act: 6.5289. Min Act: -0.1700
Data Index: 1236247 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19