Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.7454. Min Act: -0.1700
Data Index: 2087056 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.6516. Min Act: -0.1700
Data Index: 7711551 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.6516. Min Act: -0.1700
Data Index: 8265689 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.5891. Min Act: -0.1700
Data Index: 8278376 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.5266. Min Act: -0.1700
Data Index: 7466031 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4016. Min Act: -0.1700
Data Index: 532743 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4329. Min Act: -0.1700
Data Index: 8146938 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4016. Min Act: -0.1700
Data Index: 6907457 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4016. Min Act: -0.1700
Data Index: 7622734 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.4016. Min Act: -0.1700
Data Index: 6050510 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3704. Min Act: -0.1700
Data Index: 8514274 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3391. Min Act: -0.1700
Data Index: 5069851 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3704. Min Act: -0.1700
Data Index: 6559917 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3391. Min Act: -0.1699
Data Index: 5946524 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3391. Min Act: -0.1700
Data Index: 5135304 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3391. Min Act: -0.1700
Data Index: 6735396 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3391. Min Act: -0.1700
Data Index: 788451 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3704. Min Act: -0.1700
Data Index: 7652894 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3079. Min Act: -0.1700
Data Index: 6933344 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7454. Min Range: -6.7454
Max Act: 6.3079. Min Act: -0.1697
Data Index: 6017261 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19