Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.5340. Min Act: -0.1700
Data Index: 7452047 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.4403. Min Act: -0.1700
Data Index: 7561732 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.4090. Min Act: -0.1700
Data Index: 2407038 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.4090. Min Act: -0.1700
Data Index: 7161823 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3465. Min Act: -0.1700
Data Index: 4386555 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3153. Min Act: -0.1700
Data Index: 1735854 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3153. Min Act: -0.1700
Data Index: 8689350 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 1955224 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 3809149 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.3153. Min Act: -0.1700
Data Index: 4305119 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 967371 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2840. Min Act: -0.1700
Data Index: 3711154 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2528. Min Act: -0.1700
Data Index: 8718401 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2528. Min Act: -0.1700
Data Index: 6670943 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2215. Min Act: -0.1700
Data Index: 46174 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2528. Min Act: -0.1700
Data Index: 3873736 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2215. Min Act: -0.1700
Data Index: 6583869 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2215. Min Act: -0.1700
Data Index: 7165084 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.2215. Min Act: -0.1700
Data Index: 3302352 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5340. Min Range: -5.5340
Max Act: 5.1903. Min Act: -0.1700
Data Index: 7017055 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19