Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1952 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.7152. Min Act: -0.1700
Data Index: 588592 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.6215. Min Act: -0.1700
Data Index: 5113672 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.5590. Min Act: -0.1700
Data Index: 411940 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.1527. Min Act: -0.1700
Data Index: 8621522 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.1840. Min Act: -0.1700
Data Index: 2795127 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.1840. Min Act: -0.1700
Data Index: 5461193 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.1840. Min Act: -0.1700
Data Index: 1309689 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.0590. Min Act: -0.1700
Data Index: 4495675 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.0902. Min Act: -0.1700
Data Index: 8130035 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.0277. Min Act: -0.1681
Data Index: 5531383 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7152. Min Range: -8.7152
Max Act: 8.0277. Min Act: -0.1700
Data Index: 5516895 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7152. Min Range: -8.7152
Max Act: 7.9340. Min Act: -0.1700
Data Index: 3100902 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7152. Min Range: -8.7152
Max Act: 7.9652. Min Act: -0.1700
Data Index: 5961111 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7152. Min Range: -8.7152
Max Act: 7.9340. Min Act: -0.1700
Data Index: 3576524 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7152. Min Range: -8.7152
Max Act: 7.8715. Min Act: -0.1700
Data Index: 2836860 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7152. Min Range: -8.7152
Max Act: 7.9027. Min Act: -0.1700
Data Index: 4254546 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7152. Min Range: -8.7152
Max Act: 7.9027. Min Act: -0.1700
Data Index: 1552163 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7152. Min Range: -8.7152
Max Act: 7.8090. Min Act: -0.1700
Data Index: 4923198 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7152. Min Range: -8.7152
Max Act: 7.8090. Min Act: -0.1700
Data Index: 588593 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7152. Min Range: -8.7152
Max Act: 7.8090. Min Act: -0.1700
Data Index: 5366747 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19