Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3982 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2510. Min Range: -6.2510
Max Act: 6.2510. Min Act: -0.1700
Data Index: 3120258 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2510. Min Range: -6.2510
Max Act: 6.0322. Min Act: -0.1700
Data Index: 5772625 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2510. Min Range: -6.2510
Max Act: 6.0010. Min Act: -0.1700
Data Index: 1545290 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.9697. Min Act: -0.1700
Data Index: 7036843 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.9697. Min Act: -0.1700
Data Index: 5972105 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.9385. Min Act: -0.1700
Data Index: 4419966 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.8760. Min Act: -0.1700
Data Index: 1486493 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.8135. Min Act: -0.1700
Data Index: 1824516 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.8760. Min Act: -0.1700
Data Index: 2091746 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.8447. Min Act: -0.1700
Data Index: 4702017 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.8135. Min Act: -0.1700
Data Index: 653896 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.8135. Min Act: -0.1700
Data Index: 650283 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.7822. Min Act: -0.1700
Data Index: 4361350 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.7822. Min Act: -0.1700
Data Index: 1121631 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.7510. Min Act: -0.1700
Data Index: 3718158 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.7197. Min Act: -0.1700
Data Index: 7148447 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.7510. Min Act: -0.1700
Data Index: 7413381 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.6885. Min Act: -0.1700
Data Index: 4367424 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.6572. Min Act: -0.1700
Data Index: 1479903 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2510. Min Range: -6.2510
Max Act: 5.5947. Min Act: -0.1700
Data Index: 1163945 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19