Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.2135. Min Act: -0.1700
Data Index: 4421983 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.1822. Min Act: -0.1700
Data Index: 3748933 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.2135. Min Act: -0.1700
Data Index: 5986278 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.1822. Min Act: -0.1700
Data Index: 5481309 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.1822. Min Act: -0.1700
Data Index: 3340861 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.1822. Min Act: -0.1700
Data Index: 1504809 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.1822. Min Act: -0.1700
Data Index: 4189374 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.1510. Min Act: -0.1700
Data Index: 7439602 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.1197. Min Act: -0.1700
Data Index: 181352 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0885. Min Act: -0.1700
Data Index: 6371565 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0885. Min Act: -0.1700
Data Index: 2368886 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0885. Min Act: -0.1700
Data Index: 3580033 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0572. Min Act: -0.1700
Data Index: 6883599 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0885. Min Act: -0.1700
Data Index: 2290326 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0885. Min Act: -0.1700
Data Index: 8106755 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0885. Min Act: -0.1700
Data Index: 3791508 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0572. Min Act: -0.1700
Data Index: 7341259 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0572. Min Act: -0.1700
Data Index: 3359994 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0572. Min Act: -0.1700
Data Index: 3928016 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2135. Min Range: -4.2135
Max Act: 4.0572. Min Act: -0.1700
Data Index: 502030 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19