Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1498 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0530. Min Range: -8.0530
Max Act: 8.0530. Min Act: -0.1700
Data Index: 707153 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.9280. Min Act: -0.1700
Data Index: 5413118 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.8655. Min Act: -0.1700
Data Index: 8372402 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.8655. Min Act: -0.1700
Data Index: 3534160 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.8342. Min Act: -0.1700
Data Index: 1659207 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.8030. Min Act: -0.1700
Data Index: 3141513 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.7717. Min Act: -0.1700
Data Index: 8792469 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.7405. Min Act: -0.1700
Data Index: 4007634 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6780. Min Act: -0.1700
Data Index: 8130989 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6780. Min Act: -0.1700
Data Index: 6184765 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6467. Min Act: -0.1700
Data Index: 3792845 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6780. Min Act: -0.1700
Data Index: 8651073 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.7092. Min Act: -0.1700
Data Index: 5225975 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6780. Min Act: -0.1700
Data Index: 3697441 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6467. Min Act: -0.1700
Data Index: 6254507 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6155. Min Act: -0.1700
Data Index: 5949513 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6155. Min Act: -0.1700
Data Index: 8418252 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6155. Min Act: -0.1700
Data Index: 8232476 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6155. Min Act: -0.1700
Data Index: 1027550 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0530. Min Range: -8.0530
Max Act: 7.6155. Min Act: -0.1700
Data Index: 5722256 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19