Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6169. Min Range: -7.6169
Max Act: 7.6169. Min Act: -0.1700
Data Index: 6589416 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6169. Min Range: -7.6169
Max Act: 7.2106. Min Act: -0.1700
Data Index: 3797710 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6169. Min Range: -7.6169
Max Act: 7.0544. Min Act: -0.1700
Data Index: 4833852 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6169. Min Range: -7.6169
Max Act: 7.0544. Min Act: -0.1700
Data Index: 4822019 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.9919. Min Act: -0.1700
Data Index: 1946492 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.9919. Min Act: -0.1700
Data Index: 3449025 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.9919. Min Act: -0.1700
Data Index: 753768 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.9919. Min Act: -0.1700
Data Index: 6747954 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.8981. Min Act: -0.1700
Data Index: 7349929 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.8356. Min Act: -0.1700
Data Index: 7850734 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.8044. Min Act: -0.1700
Data Index: 8743377 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.8669. Min Act: -0.1700
Data Index: 2490381 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.8044. Min Act: -0.1700
Data Index: 1185674 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.8044. Min Act: -0.1700
Data Index: 389544 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.7731. Min Act: -0.1700
Data Index: 7679205 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.7731. Min Act: -0.1700
Data Index: 7599882 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.7731. Min Act: -0.1700
Data Index: 513303 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.7419. Min Act: -0.1700
Data Index: 8172311 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.7419. Min Act: -0.1700
Data Index: 5058091 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6169. Min Range: -7.6169
Max Act: 6.7419. Min Act: -0.1700
Data Index: 306149 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19