Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3598 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.5540. Min Act: -0.1700
Data Index: 3699593 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.5227. Min Act: -0.1700
Data Index: 3664145 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4913. Min Act: -0.1700
Data Index: 3803892 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4913. Min Act: -0.1700
Data Index: 6437711 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4600. Min Act: -0.1699
Data Index: 7167013 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4600. Min Act: -0.1700
Data Index: 1317714 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4600. Min Act: -0.1700
Data Index: 4873975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4600. Min Act: -0.1700
Data Index: 830622 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4600. Min Act: -0.1700
Data Index: 1327360 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4600. Min Act: -0.1700
Data Index: 568791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4600. Min Act: -0.1700
Data Index: 8726448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4600. Min Act: -0.1700
Data Index: 1076923 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4600. Min Act: -0.1700
Data Index: 6526938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4600. Min Act: -0.1700
Data Index: 6705603 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4287. Min Act: -0.1700
Data Index: 1045885 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4287. Min Act: -0.1700
Data Index: 6835952 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4287. Min Act: -0.1700
Data Index: 3419966 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4287. Min Act: -0.1700
Data Index: 3172685 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4287. Min Act: -0.1700
Data Index: 4570251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5540. Min Range: -3.5540
Max Act: 3.4287. Min Act: -0.1700
Data Index: 4411329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19