Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.4090. Min Act: -0.1700
Data Index: 6443984 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.3777. Min Act: -0.1700
Data Index: 4496225 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.3152. Min Act: -0.1700
Data Index: 5288586 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.2840. Min Act: -0.1700
Data Index: 1020616 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.2527. Min Act: -0.1700
Data Index: 8145550 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.2527. Min Act: -0.1700
Data Index: 147268 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.2527. Min Act: -0.1700
Data Index: 6443985 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1590. Min Act: -0.1700
Data Index: 8491640 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.1277. Min Act: -0.1700
Data Index: 1013286 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0652. Min Act: -0.1700
Data Index: 668514 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0965. Min Act: -0.1700
Data Index: 8740674 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0965. Min Act: -0.1700
Data Index: 7004867 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0965. Min Act: -0.1700
Data Index: 6679667 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0965. Min Act: -0.1700
Data Index: 300731 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0652. Min Act: -0.1700
Data Index: 7319742 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0340. Min Act: -0.1700
Data Index: 957099 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0027. Min Act: -0.1700
Data Index: 830527 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4090. Min Range: -5.4090
Max Act: 5.0027. Min Act: -0.1700
Data Index: 799336 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4090. Min Range: -5.4090
Max Act: 4.9402. Min Act: -0.1700
Data Index: 8239583 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4090. Min Range: -5.4090
Max Act: 4.9715. Min Act: -0.1700
Data Index: 876343 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19