Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1276 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2469. Min Range: -6.2469
Max Act: 6.2469. Min Act: -0.1700
Data Index: 854878 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.9031. Min Act: -0.1700
Data Index: 8286336 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.9031. Min Act: -0.1700
Data Index: 7551479 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.8406. Min Act: -0.1700
Data Index: 1082092 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.8406. Min Act: -0.1700
Data Index: 7738168 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.8094. Min Act: -0.1700
Data Index: 3666970 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7781. Min Act: -0.1700
Data Index: 7238384 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7781. Min Act: -0.1700
Data Index: 4323034 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7781. Min Act: -0.1700
Data Index: 6179480 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7469. Min Act: -0.1700
Data Index: 1508820 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7469. Min Act: -0.1700
Data Index: 6010238 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7156. Min Act: -0.1700
Data Index: 4135936 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7156. Min Act: -0.1700
Data Index: 2227890 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7156. Min Act: -0.1700
Data Index: 1230223 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7156. Min Act: -0.1700
Data Index: 5880954 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7156. Min Act: -0.1700
Data Index: 5625841 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.7156. Min Act: -0.1700
Data Index: 8335253 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.6844. Min Act: -0.1700
Data Index: 2914867 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.6531. Min Act: -0.1700
Data Index: 4848171 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2469. Min Range: -6.2469
Max Act: 5.6531. Min Act: -0.1700
Data Index: 4751801 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19