Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3141 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1290. Min Range: -7.1290
Max Act: 7.1290. Min Act: -0.1700
Data Index: 8817026 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1290. Min Range: -7.1290
Max Act: 7.0665. Min Act: -0.1700
Data Index: 8072530 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1290. Min Range: -7.1290
Max Act: 7.0040. Min Act: -0.1700
Data Index: 1133915 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1290. Min Range: -7.1290
Max Act: 7.0040. Min Act: -0.1700
Data Index: 7020720 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.8790. Min Act: -0.1700
Data Index: 4129882 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.8790. Min Act: -0.1700
Data Index: 8570789 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.8790. Min Act: -0.1700
Data Index: 3289946 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.8790. Min Act: -0.1700
Data Index: 6372338 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.8478. Min Act: -0.1700
Data Index: 1751051 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.8478. Min Act: -0.1700
Data Index: 867570 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.8478. Min Act: -0.1700
Data Index: 6346410 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.8165. Min Act: -0.1700
Data Index: 8166613 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.7853. Min Act: -0.1700
Data Index: 922267 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.7853. Min Act: -0.1700
Data Index: 3257204 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.7853. Min Act: -0.1700
Data Index: 1133919 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.7853. Min Act: -0.1700
Data Index: 4129881 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.7853. Min Act: -0.1700
Data Index: 392365 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.7853. Min Act: -0.1700
Data Index: 2928755 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.7540. Min Act: -0.1700
Data Index: 3533257 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1290. Min Range: -7.1290
Max Act: 6.7228. Min Act: -0.1700
Data Index: 1536106 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19