Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5603 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.4713. Min Act: -0.1700
Data Index: 4732066 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.4401. Min Act: -0.1700
Data Index: 1205935 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.4401. Min Act: -0.1700
Data Index: 1551598 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.2526. Min Act: -0.1700
Data Index: 691408 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.1901. Min Act: -0.1700
Data Index: 2028604 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.1901. Min Act: -0.1700
Data Index: 6122383 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.1588. Min Act: -0.1700
Data Index: 3297800 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.1588. Min Act: -0.1700
Data Index: 46852 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.1276. Min Act: -0.1700
Data Index: 2164336 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0963. Min Act: -0.1700
Data Index: 4916897 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0963. Min Act: -0.1700
Data Index: 7775157 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0963. Min Act: -0.1700
Data Index: 3886511 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0963. Min Act: -0.1700
Data Index: 5065234 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0651. Min Act: -0.1700
Data Index: 4380502 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0338. Min Act: -0.1700
Data Index: 2379080 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0338. Min Act: -0.1700
Data Index: 7380051 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0338. Min Act: -0.1700
Data Index: 5365451 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0026. Min Act: -0.1700
Data Index: 6990778 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0026. Min Act: -0.1700
Data Index: 1730897 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4713. Min Range: -5.4713
Max Act: 5.0026. Min Act: -0.1700
Data Index: 569765 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19