Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4055 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3697. Min Range: -10.3697
Max Act: 10.3697. Min Act: -0.1700
Data Index: 5115746 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3697. Min Range: -10.3697
Max Act: 10.1197. Min Act: -0.1700
Data Index: 6419204 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3697. Min Range: -10.3697
Max Act: 10.1197. Min Act: -0.1700
Data Index: 2665303 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.9947. Min Act: -0.1700
Data Index: 5319302 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3697. Min Range: -10.3697
Max Act: 10.0572. Min Act: -0.1700
Data Index: 6442036 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3697. Min Range: -10.3697
Max Act: 10.0572. Min Act: -0.1700
Data Index: 5919180 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.9947. Min Act: -0.1700
Data Index: 1653266 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.9947. Min Act: -0.1700
Data Index: 7326157 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.9947. Min Act: -0.1700
Data Index: 1479737 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.9947. Min Act: -0.1700
Data Index: 3940837 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.9947. Min Act: -0.1700
Data Index: 6723368 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.9322. Min Act: -0.1700
Data Index: 907422 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.9322. Min Act: -0.1700
Data Index: 5019258 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.8697. Min Act: -0.1700
Data Index: 2792098 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.8697. Min Act: -0.1700
Data Index: 7215298 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.8697. Min Act: -0.1700
Data Index: 4633118 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.8697. Min Act: -0.1700
Data Index: 5933547 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.8697. Min Act: -0.1700
Data Index: 4754146 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.8697. Min Act: -0.1700
Data Index: 3162459 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3697. Min Range: -10.3697
Max Act: 9.8697. Min Act: -0.1700
Data Index: 3869287 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19