Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3042 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.5510. Min Act: -0.1700
Data Index: 7759733 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.4260. Min Act: -0.1700
Data Index: 1743481 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.3010. Min Act: -0.1700
Data Index: 6725105 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2385. Min Act: -0.1700
Data Index: 6879980 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.2072. Min Act: -0.1700
Data Index: 6331279 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.1760. Min Act: -0.1700
Data Index: 3875840 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.1760. Min Act: -0.1700
Data Index: 1050005 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.1447. Min Act: -0.1700
Data Index: 6167354 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.1447. Min Act: -0.1700
Data Index: 2338110 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.1447. Min Act: -0.1700
Data Index: 3601880 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.1447. Min Act: -0.1700
Data Index: 7937763 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.1135. Min Act: -0.1700
Data Index: 1929220 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.0822. Min Act: -0.1700
Data Index: 7505647 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.0510. Min Act: -0.1700
Data Index: 4982679 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.0510. Min Act: -0.1700
Data Index: 4392179 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.0510. Min Act: -0.1700
Data Index: 2222329 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.0510. Min Act: -0.1700
Data Index: 3601462 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5510. Min Range: -6.5510
Max Act: 6.0510. Min Act: -0.1700
Data Index: 2267347 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5510. Min Range: -6.5510
Max Act: 5.9885. Min Act: -0.1700
Data Index: 3899353 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5510. Min Range: -6.5510
Max Act: 5.9885. Min Act: -0.1700
Data Index: 7182133 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19