Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.7842. Min Act: -0.1700
Data Index: 7486826 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.7529. Min Act: -0.1700
Data Index: 1993020 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.7216. Min Act: -0.1700
Data Index: 4610923 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.7216. Min Act: -0.1700
Data Index: 7313180 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.6277. Min Act: -0.1700
Data Index: 1979461 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.6277. Min Act: -0.1700
Data Index: 4371916 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5964. Min Act: -0.1700
Data Index: 6152055 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5651. Min Act: -0.1700
Data Index: 6167125 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5964. Min Act: -0.1700
Data Index: 3725208 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5964. Min Act: -0.1700
Data Index: 3889485 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5964. Min Act: -0.1700
Data Index: 2034428 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5964. Min Act: -0.1700
Data Index: 609517 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5964. Min Act: -0.1700
Data Index: 1798353 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5964. Min Act: -0.1700
Data Index: 687055 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5651. Min Act: -0.1700
Data Index: 1617868 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5338. Min Act: -0.1700
Data Index: 8267422 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5651. Min Act: -0.1700
Data Index: 4006165 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5651. Min Act: -0.1700
Data Index: 7192036 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5651. Min Act: -0.1700
Data Index: 374024 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7842. Min Range: -3.7842
Max Act: 3.5338. Min Act: -0.1700
Data Index: 3411696 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19