Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3151 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1045. Min Range: -4.1045
Max Act: 4.1045. Min Act: -0.1700
Data Index: 113021 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1045. Min Range: -4.1045
Max Act: 4.1045. Min Act: -0.1700
Data Index: 8634786 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1045. Min Range: -4.1045
Max Act: 4.0420. Min Act: -0.1700
Data Index: 4538899 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1045. Min Range: -4.1045
Max Act: 4.0107. Min Act: -0.1700
Data Index: 5213893 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9638. Min Act: -0.1700
Data Index: 7991994 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9638. Min Act: -0.1700
Data Index: 7456407 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9638. Min Act: -0.1700
Data Index: 4753285 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9794. Min Act: -0.1700
Data Index: 5434600 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9638. Min Act: -0.1700
Data Index: 6709795 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9482. Min Act: -0.1700
Data Index: 7233119 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9325. Min Act: -0.1700
Data Index: 4228025 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9169. Min Act: -0.1700
Data Index: 1878706 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9169. Min Act: -0.1700
Data Index: 8299987 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9169. Min Act: -0.1700
Data Index: 8300001 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9169. Min Act: -0.1700
Data Index: 4069080 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9169. Min Act: -0.1700
Data Index: 1748741 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9013. Min Act: -0.1700
Data Index: 2111037 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.9013. Min Act: -0.1700
Data Index: 1246787 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.8856. Min Act: -0.1700
Data Index: 559931 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1045. Min Range: -4.1045
Max Act: 3.8856. Min Act: -0.1700
Data Index: 8276959 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19