Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4652. Min Range: -7.4652
Max Act: 7.4652. Min Act: -0.1700
Data Index: 2136414 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4652. Min Range: -7.4652
Max Act: 7.2777. Min Act: -0.1700
Data Index: 2005262 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4652. Min Range: -7.4652
Max Act: 7.1839. Min Act: -0.1700
Data Index: 7780363 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4652. Min Range: -7.4652
Max Act: 7.2152. Min Act: -0.1700
Data Index: 4121190 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4652. Min Range: -7.4652
Max Act: 7.1214. Min Act: -0.1700
Data Index: 4077250 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4652. Min Range: -7.4652
Max Act: 7.0902. Min Act: -0.1700
Data Index: 5287485 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4652. Min Range: -7.4652
Max Act: 7.0902. Min Act: -0.1700
Data Index: 2441535 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4652. Min Range: -7.4652
Max Act: 7.0277. Min Act: -0.1700
Data Index: 8503208 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.9964. Min Act: -0.1700
Data Index: 3527734 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.9964. Min Act: -0.1700
Data Index: 6028400 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.9964. Min Act: -0.1700
Data Index: 2019216 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.9652. Min Act: -0.1700
Data Index: 8128520 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.8714. Min Act: -0.1700
Data Index: 7314023 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.8714. Min Act: -0.1700
Data Index: 3982714 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.9027. Min Act: -0.1700
Data Index: 916165 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.8714. Min Act: -0.1700
Data Index: 3184348 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.8714. Min Act: -0.1700
Data Index: 7277103 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.8714. Min Act: -0.1700
Data Index: 2125474 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.8402. Min Act: -0.1700
Data Index: 1789024 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4652. Min Range: -7.4652
Max Act: 6.8402. Min Act: -0.1700
Data Index: 8235644 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19