Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2738 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.9374. Min Act: -0.1700
Data Index: 5288823 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.8124. Min Act: -0.1700
Data Index: 5789028 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.7499. Min Act: -0.1700
Data Index: 6378217 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.5937. Min Act: -0.1700
Data Index: 7281301 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.5937. Min Act: -0.1700
Data Index: 8330153 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.4999. Min Act: -0.1700
Data Index: 34985 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.4999. Min Act: -0.1700
Data Index: 5966561 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.4687. Min Act: -0.1700
Data Index: 4380646 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.4374. Min Act: -0.1700
Data Index: 239579 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.4062. Min Act: -0.1700
Data Index: 3713040 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.4062. Min Act: -0.1700
Data Index: 7170236 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.3749. Min Act: -0.1700
Data Index: 4595454 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.3749. Min Act: -0.1700
Data Index: 4568243 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.3437. Min Act: -0.1700
Data Index: 3439240 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.3749. Min Act: -0.1700
Data Index: 628325 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.3437. Min Act: -0.1700
Data Index: 1336007 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.3437. Min Act: -0.1700
Data Index: 7796513 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.3124. Min Act: -0.1700
Data Index: 8765551 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.3437. Min Act: -0.1700
Data Index: 7991854 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9374. Min Range: -6.9374
Max Act: 6.2812. Min Act: -0.1700
Data Index: 5551914 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19