Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.5685. Min Act: -0.1700
Data Index: 6240517 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.3810. Min Act: -0.1700
Data Index: 58421 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.2560. Min Act: -0.1700
Data Index: 631755 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.1935. Min Act: -0.1700
Data Index: 4235284 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.0685. Min Act: -0.1700
Data Index: 1587759 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.0060. Min Act: -0.1700
Data Index: 8329440 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.0060. Min Act: -0.1700
Data Index: 8773103 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.0060. Min Act: -0.1700
Data Index: 6970311 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.0060. Min Act: -0.1700
Data Index: 228178 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.0060. Min Act: -0.1700
Data Index: 5143137 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5685. Min Range: -8.5685
Max Act: 8.0685. Min Act: -0.1700
Data Index: 4722989 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5685. Min Range: -8.5685
Max Act: 7.9748. Min Act: -0.1700
Data Index: 6287043 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5685. Min Range: -8.5685
Max Act: 7.9748. Min Act: -0.1700
Data Index: 3706350 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5685. Min Range: -8.5685
Max Act: 7.9123. Min Act: -0.1700
Data Index: 6477850 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5685. Min Range: -8.5685
Max Act: 7.9435. Min Act: -0.1700
Data Index: 5405675 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5685. Min Range: -8.5685
Max Act: 7.9123. Min Act: -0.1700
Data Index: 5963692 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5685. Min Range: -8.5685
Max Act: 7.9123. Min Act: -0.1700
Data Index: 197968 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5685. Min Range: -8.5685
Max Act: 7.8810. Min Act: -0.1700
Data Index: 2453380 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5685. Min Range: -8.5685
Max Act: 7.8810. Min Act: -0.1700
Data Index: 8076059 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5685. Min Range: -8.5685
Max Act: 7.8810. Min Act: -0.1700
Data Index: 5549180 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19