Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.8474. Min Act: -0.1700
Data Index: 8767729 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.5974. Min Act: -0.1700
Data Index: 552151 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.5662. Min Act: -0.1700
Data Index: 4826160 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.5662. Min Act: -0.1700
Data Index: 3252784 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.5662. Min Act: -0.1700
Data Index: 7605056 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.5037. Min Act: -0.1700
Data Index: 8500618 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.4412. Min Act: -0.1700
Data Index: 3322385 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.4099. Min Act: -0.1700
Data Index: 2453797 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.3787. Min Act: -0.1700
Data Index: 16398 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.3787. Min Act: -0.1700
Data Index: 3480204 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.3787. Min Act: -0.1700
Data Index: 370915 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.3787. Min Act: -0.1700
Data Index: 2937607 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.4099. Min Act: -0.1700
Data Index: 4584628 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.2849. Min Act: -0.1700
Data Index: 8680376 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.2849. Min Act: -0.1700
Data Index: 3679464 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.3162. Min Act: -0.1700
Data Index: 1740260 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.3162. Min Act: -0.1700
Data Index: 6584068 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.2537. Min Act: -0.1700
Data Index: 7927521 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.2224. Min Act: -0.1700
Data Index: 6642182 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8474. Min Range: -6.8474
Max Act: 6.2224. Min Act: -0.1700
Data Index: 533613 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19