Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5064 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1463. Min Range: -8.1463
Max Act: 8.1463. Min Act: -0.1700
Data Index: 3434910 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1463. Min Range: -8.1463
Max Act: 8.1463. Min Act: -0.1700
Data Index: 3031379 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1463. Min Range: -8.1463
Max Act: 8.0838. Min Act: -0.1700
Data Index: 7383294 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1463. Min Range: -8.1463
Max Act: 8.0525. Min Act: -0.1700
Data Index: 6333948 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1463. Min Range: -8.1463
Max Act: 8.0525. Min Act: -0.1700
Data Index: 7186180 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1463. Min Range: -8.1463
Max Act: 8.0213. Min Act: -0.1700
Data Index: 6802200 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1463. Min Range: -8.1463
Max Act: 8.0213. Min Act: -0.1700
Data Index: 8552419 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1463. Min Range: -8.1463
Max Act: 8.0213. Min Act: -0.1700
Data Index: 8542752 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.9900. Min Act: -0.1700
Data Index: 5873867 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.9275. Min Act: -0.1700
Data Index: 2306278 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.8963. Min Act: -0.1700
Data Index: 6600670 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.9275. Min Act: -0.1700
Data Index: 8612627 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.9275. Min Act: -0.1700
Data Index: 5730923 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.8963. Min Act: -0.1700
Data Index: 6806153 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.8650. Min Act: -0.1700
Data Index: 7991068 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.8338. Min Act: -0.1700
Data Index: 4584883 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.8650. Min Act: -0.1700
Data Index: 4065689 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.8338. Min Act: -0.1700
Data Index: 6157521 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.8025. Min Act: -0.1700
Data Index: 1867098 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1463. Min Range: -8.1463
Max Act: 7.7713. Min Act: -0.1700
Data Index: 5751410 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19