Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.9967. Min Act: -0.1700
Data Index: 6912278 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.9655. Min Act: -0.1700
Data Index: 1703168 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.9342. Min Act: -0.1700
Data Index: 5294250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.9029. Min Act: -0.1700
Data Index: 825970 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.8717. Min Act: -0.1700
Data Index: 6447120 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.8404. Min Act: -0.1700
Data Index: 4320702 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.8091. Min Act: -0.1700
Data Index: 2276820 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.8091. Min Act: -0.1700
Data Index: 8614505 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.8091. Min Act: -0.1700
Data Index: 6266656 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.8091. Min Act: -0.1700
Data Index: 1308160 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.7779. Min Act: -0.1700
Data Index: 137022 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.7779. Min Act: -0.1700
Data Index: 2896062 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.7466. Min Act: -0.1700
Data Index: 5066320 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.7466. Min Act: -0.1700
Data Index: 3465323 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.7779. Min Act: -0.1700
Data Index: 460424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.7466. Min Act: -0.1700
Data Index: 8338380 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.7466. Min Act: -0.1700
Data Index: 119704 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.7466. Min Act: -0.1700
Data Index: 598011 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.7466. Min Act: -0.1700
Data Index: 119692 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9967. Min Range: -3.9967
Max Act: 3.7153. Min Act: -0.1700
Data Index: 4307445 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19