Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5575. Min Range: -8.5575
Max Act: 8.5575. Min Act: -0.1700
Data Index: 1427702 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5575. Min Range: -8.5575
Max Act: 8.4325. Min Act: -0.1700
Data Index: 1600479 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5575. Min Range: -8.5575
Max Act: 8.1825. Min Act: -0.1700
Data Index: 6526797 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5575. Min Range: -8.5575
Max Act: 8.1825. Min Act: -0.1700
Data Index: 8795163 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5575. Min Range: -8.5575
Max Act: 8.1200. Min Act: -0.1700
Data Index: 6375394 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5575. Min Range: -8.5575
Max Act: 8.0575. Min Act: -0.1700
Data Index: 6490029 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.9950. Min Act: -0.1700
Data Index: 6954712 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.9638. Min Act: -0.1700
Data Index: 7720847 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.9638. Min Act: -0.1700
Data Index: 5815827 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.9638. Min Act: -0.1700
Data Index: 5859839 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.9325. Min Act: -0.1700
Data Index: 2634775 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.9325. Min Act: -0.1700
Data Index: 2592385 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.9325. Min Act: -0.1700
Data Index: 279137 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.9013. Min Act: -0.1700
Data Index: 8541450 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.9325. Min Act: -0.1700
Data Index: 935517 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.8700. Min Act: -0.1700
Data Index: 8767100 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.8700. Min Act: -0.1700
Data Index: 4357041 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.8388. Min Act: -0.1700
Data Index: 1275887 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.8388. Min Act: -0.1700
Data Index: 8386686 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5575. Min Range: -8.5575
Max Act: 7.8700. Min Act: -0.1700
Data Index: 5168688 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19