Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4824 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.2070. Min Act: -0.1700
Data Index: 2292875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.1757. Min Act: -0.1700
Data Index: 3991845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.1757. Min Act: -0.1700
Data Index: 2293121 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.1445. Min Act: -0.1700
Data Index: 3427015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.1132. Min Act: -0.1700
Data Index: 4728979 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0820. Min Act: -0.1700
Data Index: 2953974 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0820. Min Act: -0.1700
Data Index: 6522293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0820. Min Act: -0.1697
Data Index: 5281619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0820. Min Act: -0.1700
Data Index: 8529677 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0507. Min Act: -0.1700
Data Index: 6699595 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0195. Min Act: -0.1700
Data Index: 7841049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0507. Min Act: -0.1700
Data Index: 5575475 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0507. Min Act: -0.1700
Data Index: 5743250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0507. Min Act: -0.1700
Data Index: 8721295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0507. Min Act: -0.1699
Data Index: 6503490 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0195. Min Act: -0.1699
Data Index: 3015066 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0195. Min Act: -0.1700
Data Index: 6439675 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0507. Min Act: -0.1700
Data Index: 8077859 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0195. Min Act: -0.1700
Data Index: 7505836 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2070. Min Range: -5.2070
Max Act: 5.0195. Min Act: -0.1700
Data Index: 6573680 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19