Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5130 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0925. Min Range: -3.0925
Max Act: 3.0925. Min Act: -0.1700
Data Index: 5618518 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0925. Min Range: -3.0925
Max Act: 3.0767. Min Act: -0.1700
Data Index: 2731014 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9028. Min Act: -0.1700
Data Index: 8032402 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9028. Min Act: -0.1700
Data Index: 2724997 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.9028. Min Act: -0.1700
Data Index: 6389840 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8711. Min Act: -0.1700
Data Index: 3429897 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8869. Min Act: -0.1700
Data Index: 3262367 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8552. Min Act: -0.1700
Data Index: 2570041 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8552. Min Act: -0.1700
Data Index: 8629866 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8552. Min Act: -0.1700
Data Index: 1500436 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8393. Min Act: -0.1700
Data Index: 7035112 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8393. Min Act: -0.1700
Data Index: 4129385 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8552. Min Act: -0.1700
Data Index: 6281851 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8393. Min Act: -0.1700
Data Index: 5492983 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8234. Min Act: -0.1700
Data Index: 6268021 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8075. Min Act: -0.1700
Data Index: 182599 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8075. Min Act: -0.1700
Data Index: 3195843 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.8075. Min Act: -0.1700
Data Index: 5659814 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.7915. Min Act: -0.1700
Data Index: 8463513 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0925. Min Range: -3.0925
Max Act: 2.7915. Min Act: -0.1700
Data Index: 478677 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19