Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5877 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.4537. Min Act: -0.1700
Data Index: 2701330 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.4537. Min Act: -0.1700
Data Index: 5439946 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.2662. Min Act: -0.1700
Data Index: 1320666 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.3287. Min Act: -0.1700
Data Index: 5409743 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.3287. Min Act: -0.1700
Data Index: 5449781 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.1412. Min Act: -0.1700
Data Index: 7435015 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.1412. Min Act: -0.1700
Data Index: 2380835 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.1412. Min Act: -0.1700
Data Index: 4246718 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.1412. Min Act: -0.1700
Data Index: 5152115 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.1412. Min Act: -0.1700
Data Index: 5256403 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.1412. Min Act: -0.1700
Data Index: 7559499 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.0787. Min Act: -0.1700
Data Index: 3210600 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.0474. Min Act: -0.1700
Data Index: 2685880 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.0162. Min Act: -0.1700
Data Index: 8617595 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4537. Min Range: -8.4537
Max Act: 7.9849. Min Act: -0.1700
Data Index: 832397 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4537. Min Range: -8.4537
Max Act: 7.9849. Min Act: -0.1700
Data Index: 3781460 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4537. Min Range: -8.4537
Max Act: 7.9849. Min Act: -0.1700
Data Index: 2752840 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4537. Min Range: -8.4537
Max Act: 7.9849. Min Act: -0.1700
Data Index: 208543 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4537. Min Range: -8.4537
Max Act: 8.0162. Min Act: -0.1700
Data Index: 1056857 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4537. Min Range: -8.4537
Max Act: 7.9537. Min Act: -0.1700
Data Index: 6909710 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19