Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 233 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.5464. Min Act: -0.1700
Data Index: 8686041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.4211. Min Act: -0.1700
Data Index: 3135035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3898. Min Act: -0.1700
Data Index: 7646785 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3898. Min Act: -0.1700
Data Index: 7211883 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3898. Min Act: -0.1700
Data Index: 6333940 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3741. Min Act: -0.1700
Data Index: 4620299 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3584. Min Act: -0.1700
Data Index: 5061736 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3741. Min Act: -0.1700
Data Index: 1242824 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3741. Min Act: -0.1700
Data Index: 4146432 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3584. Min Act: -0.1700
Data Index: 3429351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3427. Min Act: -0.1700
Data Index: 702274 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3427. Min Act: -0.1700
Data Index: 6204764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3427. Min Act: -0.1700
Data Index: 1255608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3427. Min Act: -0.1700
Data Index: 343069 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3427. Min Act: -0.1700
Data Index: 7225059 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3270. Min Act: -0.1700
Data Index: 727657 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3270. Min Act: -0.1700
Data Index: 7791281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3113. Min Act: -0.1700
Data Index: 1450215 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3113. Min Act: -0.1700
Data Index: 6201263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5464. Min Range: -3.5464
Max Act: 3.3113. Min Act: -0.1700
Data Index: 6859172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19