Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.7860. Min Act: -0.1700
Data Index: 3944912 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.6922. Min Act: -0.1700
Data Index: 8491906 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.6610. Min Act: -0.1700
Data Index: 4564775 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.5985. Min Act: -0.1700
Data Index: 7125181 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.5672. Min Act: -0.1700
Data Index: 4009287 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.5360. Min Act: -0.1700
Data Index: 8734290 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.5360. Min Act: -0.1700
Data Index: 4896797 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.5360. Min Act: -0.1700
Data Index: 3566403 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.5047. Min Act: -0.1700
Data Index: 3399932 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.5047. Min Act: -0.1700
Data Index: 6580442 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.4735. Min Act: -0.1700
Data Index: 4286110 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.4735. Min Act: -0.1700
Data Index: 4546442 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.4422. Min Act: -0.1700
Data Index: 6302073 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.4735. Min Act: -0.1700
Data Index: 2139473 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.4422. Min Act: -0.1700
Data Index: 5454673 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.4422. Min Act: -0.1700
Data Index: 2589025 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.4422. Min Act: -0.1700
Data Index: 2135541 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.4422. Min Act: -0.1700
Data Index: 7159014 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.3797. Min Act: -0.1700
Data Index: 270774 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7860. Min Range: -4.7860
Max Act: 4.3797. Min Act: -0.1700
Data Index: 601075 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19