Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2490 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.8964. Min Act: -0.1700
Data Index: 6443673 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.8652. Min Act: -0.1700
Data Index: 2490625 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.8339. Min Act: -0.1700
Data Index: 5467425 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.8339. Min Act: -0.1700
Data Index: 334059 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.8339. Min Act: -0.1700
Data Index: 1792048 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.8027. Min Act: -0.1700
Data Index: 1536754 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.8027. Min Act: -0.1700
Data Index: 5502079 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.8027. Min Act: -0.1700
Data Index: 1742499 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7714. Min Act: -0.1700
Data Index: 4382679 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7714. Min Act: -0.1700
Data Index: 869819 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7714. Min Act: -0.1700
Data Index: 8749520 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7714. Min Act: -0.1700
Data Index: 7855081 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7714. Min Act: -0.1700
Data Index: 7356784 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7714. Min Act: -0.1700
Data Index: 758623 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7714. Min Act: -0.1700
Data Index: 7050394 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7714. Min Act: -0.1700
Data Index: 6999940 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7714. Min Act: -0.1700
Data Index: 5503841 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7714. Min Act: -0.1700
Data Index: 1343579 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7402. Min Act: -0.1700
Data Index: 2642582 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8964. Min Range: -4.8964
Max Act: 4.7402. Min Act: -0.1700
Data Index: 2976268 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19