Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3549 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.8885. Min Act: -0.1700
Data Index: 6094587 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.5448. Min Act: -0.1700
Data Index: 1848757 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.5135. Min Act: -0.1700
Data Index: 3526529 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.2010. Min Act: -0.1700
Data Index: 8612410 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.1385. Min Act: -0.1700
Data Index: 6612161 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.1385. Min Act: -0.1700
Data Index: 954506 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.1073. Min Act: -0.1700
Data Index: 615237 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.0760. Min Act: -0.1700
Data Index: 6343712 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.0760. Min Act: -0.1700
Data Index: 1254866 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.0448. Min Act: -0.1700
Data Index: 8176312 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8885. Min Range: -7.8885
Max Act: 6.9823. Min Act: -0.1700
Data Index: 4984039 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.0135. Min Act: -0.1700
Data Index: 4126165 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8885. Min Range: -7.8885
Max Act: 7.0135. Min Act: -0.1700
Data Index: 8774606 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8885. Min Range: -7.8885
Max Act: 6.9510. Min Act: -0.1700
Data Index: 5690615 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8885. Min Range: -7.8885
Max Act: 6.9510. Min Act: -0.1700
Data Index: 2085321 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8885. Min Range: -7.8885
Max Act: 6.9198. Min Act: -0.1700
Data Index: 5383518 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8885. Min Range: -7.8885
Max Act: 6.8885. Min Act: -0.1700
Data Index: 1435830 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8885. Min Range: -7.8885
Max Act: 6.9198. Min Act: -0.1700
Data Index: 7262989 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8885. Min Range: -7.8885
Max Act: 6.9198. Min Act: -0.1700
Data Index: 3192618 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8885. Min Range: -7.8885
Max Act: 6.9198. Min Act: -0.1700
Data Index: 4481859 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19