Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1803 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7683. Min Range: -6.7683
Max Act: 6.7683. Min Act: -0.1700
Data Index: 7260656 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7683. Min Range: -6.7683
Max Act: 6.4871. Min Act: -0.1700
Data Index: 8287267 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7683. Min Range: -6.7683
Max Act: 6.4246. Min Act: -0.1700
Data Index: 964644 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7683. Min Range: -6.7683
Max Act: 6.3308. Min Act: -0.1700
Data Index: 1651901 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7683. Min Range: -6.7683
Max Act: 6.2058. Min Act: -0.1700
Data Index: 2487395 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7683. Min Range: -6.7683
Max Act: 6.1746. Min Act: -0.1700
Data Index: 6747847 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7683. Min Range: -6.7683
Max Act: 6.1121. Min Act: -0.1700
Data Index: 8606639 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7683. Min Range: -6.7683
Max Act: 6.0808. Min Act: -0.1700
Data Index: 8179326 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7683. Min Range: -6.7683
Max Act: 6.0808. Min Act: -0.1700
Data Index: 7257365 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7683. Min Range: -6.7683
Max Act: 6.0183. Min Act: -0.1700
Data Index: 3993193 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7683. Min Range: -6.7683
Max Act: 5.9871. Min Act: -0.1700
Data Index: 3197775 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7683. Min Range: -6.7683
Max Act: 5.9558. Min Act: -0.1700
Data Index: 6317229 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7683. Min Range: -6.7683
Max Act: 5.9558. Min Act: -0.1700
Data Index: 5897396 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7683. Min Range: -6.7683
Max Act: 5.9246. Min Act: -0.1700
Data Index: 4102531 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7683. Min Range: -6.7683
Max Act: 5.8621. Min Act: -0.1700
Data Index: 5018972 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7683. Min Range: -6.7683
Max Act: 5.8621. Min Act: -0.1700
Data Index: 2504481 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7683. Min Range: -6.7683
Max Act: 5.8621. Min Act: -0.1700
Data Index: 6870514 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7683. Min Range: -6.7683
Max Act: 5.7996. Min Act: -0.1700
Data Index: 955513 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7683. Min Range: -6.7683
Max Act: 5.7996. Min Act: -0.1700
Data Index: 7388837 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7683. Min Range: -6.7683
Max Act: 5.7996. Min Act: -0.1700
Data Index: 4606109 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19