Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.6685. Min Act: -0.1700
Data Index: 1186662 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.5122. Min Act: -0.1700
Data Index: 7754558 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.2935. Min Act: -0.1700
Data Index: 4307678 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.2310. Min Act: -0.1700
Data Index: 4234693 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.1997. Min Act: -0.1700
Data Index: 6322117 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.1685. Min Act: -0.1700
Data Index: 8552912 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.1372. Min Act: -0.1700
Data Index: 1467166 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.1060. Min Act: -0.1700
Data Index: 4822774 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.0435. Min Act: -0.1700
Data Index: 3536959 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.0747. Min Act: -0.1700
Data Index: 6358273 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.0435. Min Act: -0.1700
Data Index: 7767937 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.0122. Min Act: -0.1700
Data Index: 8823932 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.0435. Min Act: -0.1700
Data Index: 2478833 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.0122. Min Act: -0.1700
Data Index: 4895097 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6685. Min Range: -6.6685
Max Act: 6.0435. Min Act: -0.1700
Data Index: 310624 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6685. Min Range: -6.6685
Max Act: 5.9497. Min Act: -0.1700
Data Index: 4784828 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6685. Min Range: -6.6685
Max Act: 5.9185. Min Act: -0.1700
Data Index: 4218673 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6685. Min Range: -6.6685
Max Act: 5.9185. Min Act: -0.1700
Data Index: 2919478 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6685. Min Range: -6.6685
Max Act: 5.9185. Min Act: -0.1700
Data Index: 809552 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6685. Min Range: -6.6685
Max Act: 5.9185. Min Act: -0.1700
Data Index: 334063 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19