Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6686. Min Range: -9.6686
Max Act: 9.6686. Min Act: -0.1700
Data Index: 8384945 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6686. Min Range: -9.6686
Max Act: 9.4811. Min Act: -0.1700
Data Index: 608577 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6686. Min Range: -9.6686
Max Act: 9.4811. Min Act: -0.1700
Data Index: 6162158 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6686. Min Range: -9.6686
Max Act: 9.4186. Min Act: -0.1700
Data Index: 2462971 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6686. Min Range: -9.6686
Max Act: 9.3561. Min Act: -0.1700
Data Index: 4924423 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6686. Min Range: -9.6686
Max Act: 9.1686. Min Act: -0.1700
Data Index: 2178132 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6686. Min Range: -9.6686
Max Act: 9.0436. Min Act: -0.1700
Data Index: 5894555 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.9186. Min Act: -0.1700
Data Index: 3487418 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.9186. Min Act: -0.1700
Data Index: 7073240 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.9186. Min Act: -0.1700
Data Index: 8279765 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.9186. Min Act: -0.1700
Data Index: 977590 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.8561. Min Act: -0.1700
Data Index: 2625896 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.7936. Min Act: -0.1700
Data Index: 2703598 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.7936. Min Act: -0.1700
Data Index: 8467236 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.7311. Min Act: -0.1700
Data Index: 202481 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.7311. Min Act: -0.1700
Data Index: 3349015 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.7311. Min Act: -0.1700
Data Index: 6907500 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.6686. Min Act: -0.1700
Data Index: 2167353 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.6061. Min Act: -0.1700
Data Index: 3375179 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6686. Min Range: -9.6686
Max Act: 8.6061. Min Act: -0.1700
Data Index: 2081026 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19