Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2894 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0058. Min Range: -5.0058
Max Act: 5.0058. Min Act: -0.1700
Data Index: 596627 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.9746. Min Act: -0.1700
Data Index: 5843137 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.9433. Min Act: -0.1700
Data Index: 8642460 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.9433. Min Act: -0.1700
Data Index: 549240 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.9121. Min Act: -0.1700
Data Index: 7022262 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.9121. Min Act: -0.1700
Data Index: 615848 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.9121. Min Act: -0.1700
Data Index: 8765744 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.9121. Min Act: -0.1700
Data Index: 7865712 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.9121. Min Act: -0.1700
Data Index: 8486106 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.9121. Min Act: -0.1700
Data Index: 4520411 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.8808. Min Act: -0.1700
Data Index: 8807396 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.8808. Min Act: -0.1700
Data Index: 4445770 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.8808. Min Act: -0.1700
Data Index: 7111285 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.8496. Min Act: -0.1700
Data Index: 3870704 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.8496. Min Act: -0.1700
Data Index: 1942870 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.8496. Min Act: -0.1700
Data Index: 2630102 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.8496. Min Act: -0.1700
Data Index: 2542527 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.8496. Min Act: -0.1700
Data Index: 4009124 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.8496. Min Act: -0.1700
Data Index: 1642537 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0058. Min Range: -5.0058
Max Act: 4.8183. Min Act: -0.1700
Data Index: 5148720 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19