Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5033 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4814. Min Range: -8.4814
Max Act: 8.4814. Min Act: -0.1700
Data Index: 5494232 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4814. Min Range: -8.4814
Max Act: 8.1064. Min Act: -0.1700
Data Index: 2992031 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4814. Min Range: -8.4814
Max Act: 8.0439. Min Act: -0.1700
Data Index: 2467827 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4814. Min Range: -8.4814
Max Act: 8.0439. Min Act: -0.1700
Data Index: 2837452 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.9814. Min Act: -0.1700
Data Index: 7275529 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.9814. Min Act: -0.1700
Data Index: 1269810 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.7939. Min Act: -0.1700
Data Index: 8036784 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.7939. Min Act: -0.1700
Data Index: 3593394 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.7314. Min Act: -0.1700
Data Index: 7400740 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.6689. Min Act: -0.1700
Data Index: 8525498 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.6376. Min Act: -0.1700
Data Index: 2115246 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.6376. Min Act: -0.1700
Data Index: 4346639 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.6064. Min Act: -0.1700
Data Index: 5024774 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.6376. Min Act: -0.1700
Data Index: 5293165 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.5751. Min Act: -0.1700
Data Index: 2154129 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.5751. Min Act: -0.1700
Data Index: 8601008 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.5439. Min Act: -0.1700
Data Index: 4921057 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.5126. Min Act: -0.1700
Data Index: 119287 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.5126. Min Act: -0.1700
Data Index: 6943336 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4814. Min Range: -8.4814
Max Act: 7.5126. Min Act: -0.1700
Data Index: 8638091 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19