Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.7646. Min Act: -0.1700
Data Index: 1173382 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.5146. Min Act: -0.1700
Data Index: 8657909 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.4521. Min Act: -0.1700
Data Index: 1951880 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.4521. Min Act: -0.1700
Data Index: 87223 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.3896. Min Act: -0.1700
Data Index: 3191230 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.3896. Min Act: -0.1700
Data Index: 901758 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.3583. Min Act: -0.1700
Data Index: 7837298 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.3271. Min Act: -0.1700
Data Index: 5001155 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.3271. Min Act: -0.1700
Data Index: 5505594 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.3271. Min Act: -0.1700
Data Index: 280768 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.2958. Min Act: -0.1700
Data Index: 1363038 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.2958. Min Act: -0.1700
Data Index: 3939272 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.2958. Min Act: -0.1700
Data Index: 1866985 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.2333. Min Act: -0.1700
Data Index: 4122537 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.2333. Min Act: -0.1700
Data Index: 895661 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.2021. Min Act: -0.1700
Data Index: 2491576 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.2333. Min Act: -0.1700
Data Index: 2995626 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.1708. Min Act: -0.1700
Data Index: 4361221 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.1708. Min Act: -0.1700
Data Index: 3817047 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7646. Min Range: -6.7646
Max Act: 6.1708. Min Act: -0.1700
Data Index: 6273756 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19