Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1473 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.9090. Min Act: -0.1700
Data Index: 3065849 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.3465. Min Act: -0.1700
Data Index: 269252 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.4403. Min Act: -0.1700
Data Index: 6824606 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.3153. Min Act: -0.1700
Data Index: 1543788 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.3153. Min Act: -0.1700
Data Index: 5475770 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.3153. Min Act: -0.1700
Data Index: 1675193 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.2528. Min Act: -0.1700
Data Index: 5311763 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.3465. Min Act: -0.1700
Data Index: 6937713 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.2215. Min Act: -0.1700
Data Index: 2701359 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.3153. Min Act: -0.1700
Data Index: 6180069 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.2528. Min Act: -0.1700
Data Index: 2062673 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.2528. Min Act: -0.1700
Data Index: 3679922 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.2215. Min Act: -0.1700
Data Index: 6348799 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.2215. Min Act: -0.1700
Data Index: 1846451 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.2215. Min Act: -0.1700
Data Index: 5477246 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.1903. Min Act: -0.1700
Data Index: 8493745 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.1903. Min Act: -0.1700
Data Index: 1797413 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.1278. Min Act: -0.1700
Data Index: 5511737 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.1590. Min Act: -0.1700
Data Index: 3584139 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9090. Min Range: -7.9090
Max Act: 7.1590. Min Act: -0.1700
Data Index: 8534486 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19