Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.6133. Min Act: -0.1700
Data Index: 5524091 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.4258. Min Act: -0.1700
Data Index: 7559044 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.3946. Min Act: -0.1700
Data Index: 1263319 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.3633. Min Act: -0.1700
Data Index: 782832 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.3321. Min Act: -0.1700
Data Index: 1153807 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.3008. Min Act: -0.1700
Data Index: 131376 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.3008. Min Act: -0.1700
Data Index: 8119478 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.2696. Min Act: -0.1700
Data Index: 1936390 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.2696. Min Act: -0.1700
Data Index: 286949 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.2696. Min Act: -0.1700
Data Index: 6409176 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.2696. Min Act: -0.1700
Data Index: 3436644 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.2071. Min Act: -0.1700
Data Index: 2466090 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.2071. Min Act: -0.1700
Data Index: 8581306 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.2071. Min Act: -0.1700
Data Index: 8821525 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.2071. Min Act: -0.1700
Data Index: 3072532 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.1758. Min Act: -0.1700
Data Index: 4277683 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.1758. Min Act: -0.1700
Data Index: 8057354 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.1758. Min Act: -0.1700
Data Index: 6438267 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.1758. Min Act: -0.1700
Data Index: 5488836 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6133. Min Range: -5.6133
Max Act: 5.1446. Min Act: -0.1700
Data Index: 7713964 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19