Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.2013. Min Act: -0.1700
Data Index: 6465434 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.1700. Min Act: -0.1700
Data Index: 8156174 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.1388. Min Act: -0.1700
Data Index: 303052 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.1388. Min Act: -0.1700
Data Index: 5004930 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.1388. Min Act: -0.1700
Data Index: 6751925 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.1075. Min Act: -0.1700
Data Index: 2650267 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.1075. Min Act: -0.1700
Data Index: 6872194 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0763. Min Act: -0.1700
Data Index: 3314243 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0763. Min Act: -0.1700
Data Index: 334864 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0763. Min Act: -0.1700
Data Index: 1889025 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0450. Min Act: -0.1700
Data Index: 467541 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0450. Min Act: -0.1700
Data Index: 6949232 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0450. Min Act: -0.1700
Data Index: 403225 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0138. Min Act: -0.1700
Data Index: 2020260 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0138. Min Act: -0.1700
Data Index: 5294449 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0138. Min Act: -0.1700
Data Index: 6972359 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0138. Min Act: -0.1698
Data Index: 4276425 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0138. Min Act: -0.1700
Data Index: 457193 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0138. Min Act: -0.1700
Data Index: 3314242 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2013. Min Range: -5.2013
Max Act: 5.0138. Min Act: -0.1700
Data Index: 1932954 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19