Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5110 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.5231. Min Act: -0.1700
Data Index: 5538963 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.3981. Min Act: -0.1700
Data Index: 3315132 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.3044. Min Act: -0.1700
Data Index: 8119947 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.3356. Min Act: -0.1700
Data Index: 6618818 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.2106. Min Act: -0.1700
Data Index: 4699000 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.2106. Min Act: -0.1700
Data Index: 4012363 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1794. Min Act: -0.1700
Data Index: 4012365 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1481. Min Act: -0.1700
Data Index: 2490954 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1481. Min Act: -0.1700
Data Index: 1321946 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1481. Min Act: -0.1700
Data Index: 32687 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1481. Min Act: -0.1700
Data Index: 6895963 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1481. Min Act: -0.1700
Data Index: 8119945 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1481. Min Act: -0.1700
Data Index: 6308066 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1794. Min Act: -0.1700
Data Index: 1622015 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.0856. Min Act: -0.1700
Data Index: 288376 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1169. Min Act: -0.1700
Data Index: 7460537 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.0856. Min Act: -0.1700
Data Index: 8632702 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1169. Min Act: -0.1700
Data Index: 3525833 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.1169. Min Act: -0.1700
Data Index: 1967771 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5231. Min Range: -4.5231
Max Act: 4.0856. Min Act: -0.1700
Data Index: 4576001 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19