Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 117 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.4574. Min Act: -0.1700
Data Index: 4216641 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.3324. Min Act: -0.1700
Data Index: 4868843 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.2699. Min Act: -0.1700
Data Index: 1667935 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.2699. Min Act: -0.1700
Data Index: 1120676 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.1449. Min Act: -0.1700
Data Index: 6077626 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.1761. Min Act: -0.1700
Data Index: 750711 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.1449. Min Act: -0.1700
Data Index: 3114112 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.1761. Min Act: -0.1700
Data Index: 1111687 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.1761. Min Act: -0.1700
Data Index: 2645784 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.1136. Min Act: -0.1700
Data Index: 659041 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.1136. Min Act: -0.1700
Data Index: 6164223 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.0511. Min Act: -0.1700
Data Index: 7265129 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.0511. Min Act: -0.1700
Data Index: 3781283 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.0199. Min Act: -0.1700
Data Index: 5961590 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4574. Min Range: -5.4574
Max Act: 4.9886. Min Act: -0.1700
Data Index: 8432435 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4574. Min Range: -5.4574
Max Act: 4.9886. Min Act: -0.1700
Data Index: 3677838 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4574. Min Range: -5.4574
Max Act: 4.9886. Min Act: -0.1700
Data Index: 3365058 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4574. Min Range: -5.4574
Max Act: 4.9886. Min Act: -0.1700
Data Index: 3075271 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4574. Min Range: -5.4574
Max Act: 4.9886. Min Act: -0.1700
Data Index: 675580 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4574. Min Range: -5.4574
Max Act: 5.0199. Min Act: -0.1700
Data Index: 6061043 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19