Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.6342. Min Act: -0.1700
Data Index: 1556461 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.2592. Min Act: -0.1700
Data Index: 5317520 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.2592. Min Act: -0.1700
Data Index: 2491137 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.2280. Min Act: -0.1700
Data Index: 6004722 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.2280. Min Act: -0.1700
Data Index: 4120903 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.1967. Min Act: -0.1700
Data Index: 6241371 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.1967. Min Act: -0.1700
Data Index: 4444450 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.1655. Min Act: -0.1700
Data Index: 6176016 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.1655. Min Act: -0.1700
Data Index: 1241329 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.1342. Min Act: -0.1700
Data Index: 1427673 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.1030. Min Act: -0.1700
Data Index: 939541 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.1030. Min Act: -0.1700
Data Index: 8449103 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.1030. Min Act: -0.1700
Data Index: 4064304 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.0717. Min Act: -0.1700
Data Index: 8035417 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.0717. Min Act: -0.1700
Data Index: 6176005 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.0405. Min Act: -0.1700
Data Index: 6510899 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.0092. Min Act: -0.1700
Data Index: 7134004 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6342. Min Range: -6.6342
Max Act: 6.0092. Min Act: -0.1700
Data Index: 2000056 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6342. Min Range: -6.6342
Max Act: 5.9780. Min Act: -0.1700
Data Index: 2700075 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6342. Min Range: -6.6342
Max Act: 5.9780. Min Act: -0.1700
Data Index: 112205 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19