Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2776 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.2686. Min Act: -0.1700
Data Index: 7802008 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.2061. Min Act: -0.1700
Data Index: 5595296 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.1749. Min Act: -0.1700
Data Index: 4893056 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.1749. Min Act: -0.1700
Data Index: 7119622 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.1749. Min Act: -0.1700
Data Index: 4057374 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.1436. Min Act: -0.1700
Data Index: 769850 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.1749. Min Act: -0.1700
Data Index: 8483741 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.1124. Min Act: -0.1700
Data Index: 4456672 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.0811. Min Act: -0.1700
Data Index: 4894402 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.0811. Min Act: -0.1700
Data Index: 814873 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.0499. Min Act: -0.1700
Data Index: 854193 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.0186. Min Act: -0.1700
Data Index: 5147412 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.0186. Min Act: -0.1700
Data Index: 641117 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2686. Min Range: -6.2686
Max Act: 5.9874. Min Act: -0.1700
Data Index: 3206909 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2686. Min Range: -6.2686
Max Act: 5.9874. Min Act: -0.1700
Data Index: 6451192 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2686. Min Range: -6.2686
Max Act: 5.9874. Min Act: -0.1700
Data Index: 4687144 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2686. Min Range: -6.2686
Max Act: 5.9874. Min Act: -0.1700
Data Index: 6450178 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2686. Min Range: -6.2686
Max Act: 6.0186. Min Act: -0.1700
Data Index: 2203201 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2686. Min Range: -6.2686
Max Act: 5.9561. Min Act: -0.1700
Data Index: 1713349 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2686. Min Range: -6.2686
Max Act: 5.9561. Min Act: -0.1700
Data Index: 1180971 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19