Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4435 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.7669. Min Act: -0.1700
Data Index: 5275486 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.7044. Min Act: -0.1700
Data Index: 7387332 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.5482. Min Act: -0.1700
Data Index: 1312423 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.5482. Min Act: -0.1700
Data Index: 8281342 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.5169. Min Act: -0.1700
Data Index: 7380997 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.4857. Min Act: -0.1700
Data Index: 1079927 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.4544. Min Act: -0.1700
Data Index: 5541721 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.4544. Min Act: -0.1700
Data Index: 7387334 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.4232. Min Act: -0.1700
Data Index: 6513306 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.3607. Min Act: -0.1700
Data Index: 331914 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.3607. Min Act: -0.1700
Data Index: 4371798 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.3294. Min Act: -0.1700
Data Index: 2736184 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.3294. Min Act: -0.1700
Data Index: 341090 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.2982. Min Act: -0.1700
Data Index: 6821298 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.2669. Min Act: -0.1700
Data Index: 8282785 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.2669. Min Act: -0.1700
Data Index: 1938646 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.2669. Min Act: -0.1700
Data Index: 564476 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.2044. Min Act: -0.1700
Data Index: 2131206 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.2044. Min Act: -0.1700
Data Index: 1572844 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7669. Min Range: -6.7669
Max Act: 6.2044. Min Act: -0.1700
Data Index: 2508572 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19