Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1693 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.9873. Min Act: -0.1700
Data Index: 7591831 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.9557. Min Act: -0.1700
Data Index: 4262116 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.9398. Min Act: -0.1700
Data Index: 4614451 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8923. Min Act: -0.1700
Data Index: 1851929 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8923. Min Act: -0.1700
Data Index: 8588239 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8764. Min Act: -0.1700
Data Index: 4114986 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8605. Min Act: -0.1700
Data Index: 5025606 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8605. Min Act: -0.1700
Data Index: 2212131 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8764. Min Act: -0.1700
Data Index: 6880843 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8764. Min Act: -0.1700
Data Index: 4616700 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8764. Min Act: -0.1700
Data Index: 1683973 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8446. Min Act: -0.1700
Data Index: 6247620 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8446. Min Act: -0.1700
Data Index: 6539641 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8287. Min Act: -0.1700
Data Index: 6583237 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8446. Min Act: -0.1700
Data Index: 1933630 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8287. Min Act: -0.1700
Data Index: 1320928 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8446. Min Act: -0.1700
Data Index: 3083838 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8287. Min Act: -0.1700
Data Index: 3805147 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8128. Min Act: -0.1700
Data Index: 1816118 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9873. Min Range: -2.9873
Max Act: 2.8287. Min Act: -0.1700
Data Index: 4820529 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19