Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4351 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0802. Min Range: -7.0802
Max Act: 7.0802. Min Act: -0.1700
Data Index: 2170375 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.9865. Min Act: -0.1700
Data Index: 7641145 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.9552. Min Act: -0.1700
Data Index: 6052808 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.9240. Min Act: -0.1700
Data Index: 6764395 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.8927. Min Act: -0.1700
Data Index: 5589681 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.8927. Min Act: -0.1700
Data Index: 2587456 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.8302. Min Act: -0.1700
Data Index: 6502269 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.8302. Min Act: -0.1700
Data Index: 8097978 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.8302. Min Act: -0.1700
Data Index: 1291379 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.8302. Min Act: -0.1700
Data Index: 7167015 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.7990. Min Act: -0.1700
Data Index: 2931786 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.8302. Min Act: -0.1700
Data Index: 3191679 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.7990. Min Act: -0.1700
Data Index: 8435399 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.7990. Min Act: -0.1700
Data Index: 3653380 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.7365. Min Act: -0.1700
Data Index: 474562 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.7677. Min Act: -0.1700
Data Index: 3041717 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.7052. Min Act: -0.1700
Data Index: 6232773 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.7052. Min Act: -0.1700
Data Index: 319397 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.7052. Min Act: -0.1700
Data Index: 1296790 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0802. Min Range: -7.0802
Max Act: 6.6740. Min Act: -0.1700
Data Index: 2989409 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19