Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5041 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.8360. Min Act: -0.1700
Data Index: 7990195 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.7735. Min Act: -0.1700
Data Index: 6930426 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.7110. Min Act: -0.1700
Data Index: 6747190 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.6485. Min Act: -0.1700
Data Index: 6813096 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.5860. Min Act: -0.1700
Data Index: 569337 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.4610. Min Act: -0.1700
Data Index: 6745959 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.3360. Min Act: -0.1700
Data Index: 6029756 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.3985. Min Act: -0.1700
Data Index: 613543 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.3985. Min Act: -0.1700
Data Index: 6329741 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.4610. Min Act: -0.1700
Data Index: 4491221 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.3985. Min Act: -0.1700
Data Index: 7387822 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.3985. Min Act: -0.1700
Data Index: 5065831 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.3985. Min Act: -0.1700
Data Index: 2292585 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.3360. Min Act: -0.1700
Data Index: 5059211 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.2735. Min Act: -0.1700
Data Index: 4339732 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.2735. Min Act: -0.1700
Data Index: 6299792 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.2735. Min Act: -0.1700
Data Index: 474571 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.2735. Min Act: -0.1700
Data Index: 1735110 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.2110. Min Act: -0.1700
Data Index: 1333005 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8360. Min Range: -9.8360
Max Act: 9.2110. Min Act: -0.1700
Data Index: 5019606 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19