Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2257 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.2449. Min Act: -0.1700
Data Index: 5042109 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.2137. Min Act: -0.1700
Data Index: 2991788 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.1824. Min Act: -0.1700
Data Index: 4044929 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.1824. Min Act: -0.1700
Data Index: 4750234 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.1512. Min Act: -0.1700
Data Index: 200838 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.1512. Min Act: -0.1700
Data Index: 3793593 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.1512. Min Act: -0.1700
Data Index: 728348 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.1512. Min Act: -0.1700
Data Index: 6180615 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.1199. Min Act: -0.1700
Data Index: 8022052 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.0887. Min Act: -0.1700
Data Index: 6719690 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.0887. Min Act: -0.1700
Data Index: 3394887 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.0574. Min Act: -0.1700
Data Index: 7438795 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.0574. Min Act: -0.1700
Data Index: 1538513 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.0574. Min Act: -0.1700
Data Index: 2433731 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.0262. Min Act: -0.1700
Data Index: 2138887 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.0262. Min Act: -0.1700
Data Index: 3169871 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.0262. Min Act: -0.1700
Data Index: 8458068 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.0262. Min Act: -0.1700
Data Index: 8612378 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2449. Min Range: -6.2449
Max Act: 6.0262. Min Act: -0.1700
Data Index: 602836 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2449. Min Range: -6.2449
Max Act: 5.9949. Min Act: -0.1700
Data Index: 24466 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19