Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5758 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.5622. Min Act: -0.1700
Data Index: 1010874 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.5310. Min Act: -0.1700
Data Index: 4276817 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.4685. Min Act: -0.1700
Data Index: 8622016 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.4372. Min Act: -0.1700
Data Index: 1411252 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.4685. Min Act: -0.1700
Data Index: 856255 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.4060. Min Act: -0.1700
Data Index: 8479720 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.4060. Min Act: -0.1700
Data Index: 3147335 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.3122. Min Act: -0.1700
Data Index: 982844 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.3122. Min Act: -0.1700
Data Index: 3147340 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.3122. Min Act: -0.1700
Data Index: 8832690 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.3122. Min Act: -0.1700
Data Index: 3423750 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.2810. Min Act: -0.1700
Data Index: 7664174 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.2810. Min Act: -0.1700
Data Index: 7080544 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.2185. Min Act: -0.1700
Data Index: 6157180 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.2185. Min Act: -0.1700
Data Index: 161249 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.2185. Min Act: -0.1700
Data Index: 5841899 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.2185. Min Act: -0.1700
Data Index: 6230192 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.1872. Min Act: -0.1700
Data Index: 530316 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.1872. Min Act: -0.1700
Data Index: 1105315 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5622. Min Range: -6.5622
Max Act: 6.1560. Min Act: -0.1700
Data Index: 7030205 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19