Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1494. Min Range: -8.1494
Max Act: 8.1494. Min Act: -0.1700
Data Index: 237714 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.9932. Min Act: -0.1700
Data Index: 5847113 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.8682. Min Act: -0.1700
Data Index: 3045827 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.6807. Min Act: -0.1700
Data Index: 7506915 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.6494. Min Act: -0.1700
Data Index: 7666611 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.6494. Min Act: -0.1700
Data Index: 6712620 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.6182. Min Act: -0.1700
Data Index: 7740485 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.5557. Min Act: -0.1700
Data Index: 1895486 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.4619. Min Act: -0.1700
Data Index: 6997768 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.3682. Min Act: -0.1700
Data Index: 6840757 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.3994. Min Act: -0.1700
Data Index: 6202153 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.3994. Min Act: -0.1700
Data Index: 2840961 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.3369. Min Act: -0.1700
Data Index: 5265131 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.3682. Min Act: -0.1700
Data Index: 7694368 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.3682. Min Act: -0.1700
Data Index: 6373052 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.3369. Min Act: -0.1700
Data Index: 1077503 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.2432. Min Act: -0.1700
Data Index: 7916637 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.2432. Min Act: -0.1700
Data Index: 573812 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.1807. Min Act: -0.1700
Data Index: 182307 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1494. Min Range: -8.1494
Max Act: 7.1807. Min Act: -0.1700
Data Index: 2839818 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19