Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.9618. Min Act: -0.1700
Data Index: 4933081 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.9930. Min Act: -0.1700
Data Index: 2531257 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.8680. Min Act: -0.1700
Data Index: 1422541 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.8055. Min Act: -0.1700
Data Index: 8545082 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.7743. Min Act: -0.1700
Data Index: 2151984 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.7743. Min Act: -0.1700
Data Index: 7354038 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.7430. Min Act: -0.1700
Data Index: 5711446 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.7430. Min Act: -0.1700
Data Index: 2256423 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.7430. Min Act: -0.1700
Data Index: 4039032 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.7430. Min Act: -0.1700
Data Index: 3410940 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.7430. Min Act: -0.1700
Data Index: 7886687 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.6805. Min Act: -0.1700
Data Index: 1846046 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.6805. Min Act: -0.1700
Data Index: 5986841 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.6805. Min Act: -0.1700
Data Index: 2708818 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.6180. Min Act: -0.1700
Data Index: 2853518 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.6180. Min Act: -0.1700
Data Index: 2761323 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.6180. Min Act: -0.1700
Data Index: 1332442 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.6180. Min Act: -0.1700
Data Index: 256848 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.5868. Min Act: -0.1700
Data Index: 2736135 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9930. Min Range: -6.9930
Max Act: 6.5868. Min Act: -0.1700
Data Index: 5018592 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19