Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5116 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.8802. Min Act: -0.1700
Data Index: 3070791 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.8490. Min Act: -0.1700
Data Index: 5757656 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.8177. Min Act: -0.1700
Data Index: 4693794 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.7240. Min Act: -0.1700
Data Index: 5687917 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.7552. Min Act: -0.1700
Data Index: 6941300 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6927. Min Act: -0.1700
Data Index: 2927344 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6927. Min Act: -0.1700
Data Index: 118962 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6927. Min Act: -0.1700
Data Index: 594011 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6927. Min Act: -0.1700
Data Index: 1049826 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6302. Min Act: -0.1700
Data Index: 868314 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6615. Min Act: -0.1700
Data Index: 6992906 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6615. Min Act: -0.1700
Data Index: 8712283 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6615. Min Act: -0.1700
Data Index: 336133 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6615. Min Act: -0.1700
Data Index: 4693793 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6615. Min Act: -0.1700
Data Index: 4406799 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6615. Min Act: -0.1700
Data Index: 290758 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6302. Min Act: -0.1700
Data Index: 5468681 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6302. Min Act: -0.1700
Data Index: 6593101 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.5990. Min Act: -0.1700
Data Index: 8590669 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8802. Min Range: -6.8802
Max Act: 6.6302. Min Act: -0.1700
Data Index: 2719239 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19