Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5434 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.7352. Min Act: -0.1700
Data Index: 8086833 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.7039. Min Act: -0.1700
Data Index: 7039706 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.4852. Min Act: -0.1700
Data Index: 8111742 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.4852. Min Act: -0.1700
Data Index: 3536307 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.3914. Min Act: -0.1700
Data Index: 7398626 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.3914. Min Act: -0.1700
Data Index: 8172442 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.3602. Min Act: -0.1700
Data Index: 5732244 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.3602. Min Act: -0.1700
Data Index: 8622816 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.3602. Min Act: -0.1700
Data Index: 4945525 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.2352. Min Act: -0.1700
Data Index: 6732429 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.2664. Min Act: -0.1700
Data Index: 1068100 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.2039. Min Act: -0.1700
Data Index: 4089027 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.2039. Min Act: -0.1700
Data Index: 6783683 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.1727. Min Act: -0.1700
Data Index: 1658143 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.1727. Min Act: -0.1700
Data Index: 8127455 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.1414. Min Act: -0.1700
Data Index: 2297694 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.1414. Min Act: -0.1700
Data Index: 3284248 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.1414. Min Act: -0.1700
Data Index: 8154045 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.1414. Min Act: -0.1700
Data Index: 6480723 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7352. Min Range: -6.7352
Max Act: 6.1414. Min Act: -0.1700
Data Index: 2651963 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19