Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 702 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.6168. Min Act: -0.1700
Data Index: 6527360 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.6168. Min Act: -0.1700
Data Index: 5744112 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.5543. Min Act: -0.1700
Data Index: 3473217 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.3356. Min Act: -0.1700
Data Index: 7701412 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.1793. Min Act: -0.1700
Data Index: 3217834 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.2106. Min Act: -0.1700
Data Index: 8801952 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.1793. Min Act: -0.1700
Data Index: 3623906 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.2106. Min Act: -0.1700
Data Index: 3217838 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.1481. Min Act: -0.1700
Data Index: 2613544 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.1481. Min Act: -0.1700
Data Index: 6776739 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.1168. Min Act: -0.1700
Data Index: 804856 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.0231. Min Act: -0.1700
Data Index: 7780595 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.0543. Min Act: -0.1700
Data Index: 2613563 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.0231. Min Act: -0.1700
Data Index: 837724 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6168. Min Range: -7.6168
Max Act: 7.0231. Min Act: -0.1700
Data Index: 4089542 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6168. Min Range: -7.6168
Max Act: 6.9918. Min Act: -0.1700
Data Index: 5316794 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6168. Min Range: -7.6168
Max Act: 6.9918. Min Act: -0.1700
Data Index: 5316797 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6168. Min Range: -7.6168
Max Act: 6.9918. Min Act: -0.1700
Data Index: 7780590 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6168. Min Range: -7.6168
Max Act: 6.9606. Min Act: -0.1700
Data Index: 7290939 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6168. Min Range: -7.6168
Max Act: 6.9606. Min Act: -0.1700
Data Index: 3781079 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19